Upload folder using huggingface_hub
Browse files- README.md +4 -4
- config.json +207 -22
- generation_config.json +6 -0
- model.safetensors +2 -2
- model.safetensors.index.json +1 -315
- processor_config.json +3 -2
- special_tokens_map.json +1 -0
- tokenizer_config.json +4 -0
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
license: other
|
| 5 |
license_name: tongyi-qianwen-research
|
| 6 |
license_link: LICENSE
|
| 7 |
pipeline_tag: image-text-to-text
|
|
|
|
|
|
|
| 8 |
tags:
|
| 9 |
- vision
|
| 10 |
- image-text-to-text
|
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# mlx-community/llava-interleave-qwen-0.5b-8bit
|
| 15 |
-
This model was converted to MLX format from [`llava-hf/llava-interleave-qwen-0.5b-hf`]() using mlx-vlm version **0.
|
| 16 |
Refer to the [original model card](https://huggingface.co/llava-hf/llava-interleave-qwen-0.5b-hf) for more details on the model.
|
| 17 |
## Use with mlx
|
| 18 |
|
|
@@ -21,5 +21,5 @@ pip install -U mlx-vlm
|
|
| 21 |
```
|
| 22 |
|
| 23 |
```bash
|
| 24 |
-
python -m mlx_vlm.generate --model mlx-community/llava-interleave-qwen-0.5b-8bit --max-tokens 100 --
|
| 25 |
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: tongyi-qianwen-research
|
| 4 |
license_link: LICENSE
|
| 5 |
pipeline_tag: image-text-to-text
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
tags:
|
| 9 |
- vision
|
| 10 |
- image-text-to-text
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# mlx-community/llava-interleave-qwen-0.5b-8bit
|
| 15 |
+
This model was converted to MLX format from [`llava-hf/llava-interleave-qwen-0.5b-hf`]() using mlx-vlm version **0.1.21**.
|
| 16 |
Refer to the [original model card](https://huggingface.co/llava-hf/llava-interleave-qwen-0.5b-hf) for more details on the model.
|
| 17 |
## Use with mlx
|
| 18 |
|
|
|
|
| 21 |
```
|
| 22 |
|
| 23 |
```bash
|
| 24 |
+
python -m mlx_vlm.generate --model mlx-community/llava-interleave-qwen-0.5b-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
|
| 25 |
```
|
config.json
CHANGED
|
@@ -1,50 +1,235 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"LlavaForConditionalGeneration"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"ignore_index": -100,
|
|
|
|
| 6 |
"image_token_index": 151646,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"model_type": "llava",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"projector_hidden_act": "gelu",
|
|
|
|
| 9 |
"quantization": {
|
| 10 |
"group_size": 64,
|
| 11 |
"bits": 8
|
| 12 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"text_config": {
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"Qwen2ForCausalLM"
|
| 17 |
-
],
|
| 18 |
-
"bos_token_id": 151643,
|
| 19 |
-
"eos_token_id": 151645,
|
| 20 |
"hidden_size": 1024,
|
| 21 |
"intermediate_size": 2816,
|
| 22 |
-
"max_position_embeddings": 32768,
|
| 23 |
-
"max_window_layers": 21,
|
| 24 |
-
"model_type": "qwen2",
|
| 25 |
-
"num_attention_heads": 16,
|
| 26 |
"num_hidden_layers": 24,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"num_key_value_heads": 16,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"rope_theta": 1000000.0,
|
| 29 |
-
"
|
| 30 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
-
"
|
| 33 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
"torch_dtype": "bfloat16",
|
| 36 |
-
"
|
|
|
|
|
|
|
|
|
|
| 37 |
"vision_config": {
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
"model_type": "siglip_vision_model",
|
| 44 |
-
"
|
|
|
|
|
|
|
| 45 |
"num_hidden_layers": 26,
|
|
|
|
|
|
|
| 46 |
"patch_size": 14,
|
| 47 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
},
|
| 49 |
"vision_feature_layer": -1,
|
| 50 |
"vision_feature_select_strategy": "full"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_attn_implementation_autoset": false,
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
"architectures": [
|
| 5 |
"LlavaForConditionalGeneration"
|
| 6 |
],
|
| 7 |
+
"bad_words_ids": null,
|
| 8 |
+
"begin_suppress_tokens": null,
|
| 9 |
+
"bos_token_id": null,
|
| 10 |
+
"chunk_size_feed_forward": 0,
|
| 11 |
+
"cross_attention_hidden_size": null,
|
| 12 |
+
"decoder_start_token_id": null,
|
| 13 |
+
"diversity_penalty": 0.0,
|
| 14 |
+
"do_sample": false,
|
| 15 |
+
"early_stopping": false,
|
| 16 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 17 |
+
"eos_token_id": null,
|
| 18 |
+
"exponential_decay_length_penalty": null,
|
| 19 |
+
"finetuning_task": null,
|
| 20 |
+
"forced_bos_token_id": null,
|
| 21 |
+
"forced_eos_token_id": null,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "LABEL_0",
|
| 24 |
+
"1": "LABEL_1"
|
| 25 |
+
},
|
| 26 |
"ignore_index": -100,
|
| 27 |
+
"image_seq_length": 576,
|
| 28 |
"image_token_index": 151646,
|
| 29 |
+
"is_decoder": false,
|
| 30 |
+
"is_encoder_decoder": false,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"LABEL_0": 0,
|
| 33 |
+
"LABEL_1": 1
|
| 34 |
+
},
|
| 35 |
+
"length_penalty": 1.0,
|
| 36 |
+
"max_length": 20,
|
| 37 |
+
"min_length": 0,
|
| 38 |
"model_type": "llava",
|
| 39 |
+
"multimodal_projector_bias": true,
|
| 40 |
+
"no_repeat_ngram_size": 0,
|
| 41 |
+
"num_beam_groups": 1,
|
| 42 |
+
"num_beams": 1,
|
| 43 |
+
"num_return_sequences": 1,
|
| 44 |
+
"output_attentions": false,
|
| 45 |
+
"output_hidden_states": false,
|
| 46 |
+
"output_scores": false,
|
| 47 |
+
"pad_token_id": null,
|
| 48 |
+
"prefix": null,
|
| 49 |
+
"problem_type": null,
|
| 50 |
"projector_hidden_act": "gelu",
|
| 51 |
+
"pruned_heads": {},
|
| 52 |
"quantization": {
|
| 53 |
"group_size": 64,
|
| 54 |
"bits": 8
|
| 55 |
},
|
| 56 |
+
"remove_invalid_values": false,
|
| 57 |
+
"repetition_penalty": 1.0,
|
| 58 |
+
"return_dict": true,
|
| 59 |
+
"return_dict_in_generate": false,
|
| 60 |
+
"sep_token_id": null,
|
| 61 |
+
"suppress_tokens": null,
|
| 62 |
+
"task_specific_params": null,
|
| 63 |
+
"temperature": 1.0,
|
| 64 |
"text_config": {
|
| 65 |
+
"vocab_size": 152000,
|
| 66 |
+
"max_position_embeddings": 32768,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"hidden_size": 1024,
|
| 68 |
"intermediate_size": 2816,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
"num_hidden_layers": 24,
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"use_sliding_window": false,
|
| 72 |
+
"sliding_window": 32768,
|
| 73 |
+
"max_window_layers": 21,
|
| 74 |
"num_key_value_heads": 16,
|
| 75 |
+
"hidden_act": "silu",
|
| 76 |
+
"initializer_range": 0.02,
|
| 77 |
+
"rms_norm_eps": 1e-06,
|
| 78 |
+
"use_cache": true,
|
| 79 |
"rope_theta": 1000000.0,
|
| 80 |
+
"rope_scaling": null,
|
| 81 |
+
"attention_dropout": 0.0,
|
| 82 |
+
"return_dict": true,
|
| 83 |
+
"output_hidden_states": false,
|
| 84 |
+
"output_attentions": false,
|
| 85 |
+
"torchscript": false,
|
| 86 |
"torch_dtype": "bfloat16",
|
| 87 |
+
"use_bfloat16": false,
|
| 88 |
+
"tf_legacy_loss": false,
|
| 89 |
+
"pruned_heads": {},
|
| 90 |
+
"tie_word_embeddings": true,
|
| 91 |
+
"chunk_size_feed_forward": 0,
|
| 92 |
+
"is_encoder_decoder": false,
|
| 93 |
+
"is_decoder": false,
|
| 94 |
+
"cross_attention_hidden_size": null,
|
| 95 |
+
"add_cross_attention": false,
|
| 96 |
+
"tie_encoder_decoder": false,
|
| 97 |
+
"max_length": 20,
|
| 98 |
+
"min_length": 0,
|
| 99 |
+
"do_sample": false,
|
| 100 |
+
"early_stopping": false,
|
| 101 |
+
"num_beams": 1,
|
| 102 |
+
"num_beam_groups": 1,
|
| 103 |
+
"diversity_penalty": 0.0,
|
| 104 |
+
"temperature": 1.0,
|
| 105 |
+
"top_k": 50,
|
| 106 |
+
"top_p": 1.0,
|
| 107 |
+
"typical_p": 1.0,
|
| 108 |
+
"repetition_penalty": 1.0,
|
| 109 |
+
"length_penalty": 1.0,
|
| 110 |
+
"no_repeat_ngram_size": 0,
|
| 111 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 112 |
+
"bad_words_ids": null,
|
| 113 |
+
"num_return_sequences": 1,
|
| 114 |
+
"output_scores": false,
|
| 115 |
+
"return_dict_in_generate": false,
|
| 116 |
+
"forced_bos_token_id": null,
|
| 117 |
+
"forced_eos_token_id": null,
|
| 118 |
+
"remove_invalid_values": false,
|
| 119 |
+
"exponential_decay_length_penalty": null,
|
| 120 |
+
"suppress_tokens": null,
|
| 121 |
+
"begin_suppress_tokens": null,
|
| 122 |
+
"architectures": [
|
| 123 |
+
"Qwen2ForCausalLM"
|
| 124 |
+
],
|
| 125 |
+
"finetuning_task": null,
|
| 126 |
+
"id2label": {
|
| 127 |
+
"0": "LABEL_0",
|
| 128 |
+
"1": "LABEL_1"
|
| 129 |
+
},
|
| 130 |
+
"label2id": {
|
| 131 |
+
"LABEL_0": 0,
|
| 132 |
+
"LABEL_1": 1
|
| 133 |
+
},
|
| 134 |
+
"tokenizer_class": null,
|
| 135 |
+
"prefix": null,
|
| 136 |
+
"bos_token_id": 151643,
|
| 137 |
+
"pad_token_id": null,
|
| 138 |
+
"eos_token_id": 151645,
|
| 139 |
+
"sep_token_id": null,
|
| 140 |
+
"decoder_start_token_id": null,
|
| 141 |
+
"task_specific_params": null,
|
| 142 |
+
"problem_type": null,
|
| 143 |
+
"_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
|
| 144 |
+
"_attn_implementation_autoset": false,
|
| 145 |
+
"model_type": "qwen2"
|
| 146 |
},
|
| 147 |
+
"tf_legacy_loss": false,
|
| 148 |
+
"tie_encoder_decoder": false,
|
| 149 |
+
"tie_word_embeddings": true,
|
| 150 |
+
"tokenizer_class": null,
|
| 151 |
+
"top_k": 50,
|
| 152 |
+
"top_p": 1.0,
|
| 153 |
"torch_dtype": "bfloat16",
|
| 154 |
+
"torchscript": false,
|
| 155 |
+
"transformers_version": "4.50.2",
|
| 156 |
+
"typical_p": 1.0,
|
| 157 |
+
"use_bfloat16": false,
|
| 158 |
"vision_config": {
|
| 159 |
+
"return_dict": true,
|
| 160 |
+
"output_hidden_states": false,
|
| 161 |
+
"output_attentions": false,
|
| 162 |
+
"torchscript": false,
|
| 163 |
+
"torch_dtype": null,
|
| 164 |
+
"use_bfloat16": false,
|
| 165 |
+
"tf_legacy_loss": false,
|
| 166 |
+
"pruned_heads": {},
|
| 167 |
+
"tie_word_embeddings": true,
|
| 168 |
+
"chunk_size_feed_forward": 0,
|
| 169 |
+
"is_encoder_decoder": false,
|
| 170 |
+
"is_decoder": false,
|
| 171 |
+
"cross_attention_hidden_size": null,
|
| 172 |
+
"add_cross_attention": false,
|
| 173 |
+
"tie_encoder_decoder": false,
|
| 174 |
+
"max_length": 20,
|
| 175 |
+
"min_length": 0,
|
| 176 |
+
"do_sample": false,
|
| 177 |
+
"early_stopping": false,
|
| 178 |
+
"num_beams": 1,
|
| 179 |
+
"num_beam_groups": 1,
|
| 180 |
+
"diversity_penalty": 0.0,
|
| 181 |
+
"temperature": 1.0,
|
| 182 |
+
"top_k": 50,
|
| 183 |
+
"top_p": 1.0,
|
| 184 |
+
"typical_p": 1.0,
|
| 185 |
+
"repetition_penalty": 1.0,
|
| 186 |
+
"length_penalty": 1.0,
|
| 187 |
+
"no_repeat_ngram_size": 0,
|
| 188 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 189 |
+
"bad_words_ids": null,
|
| 190 |
+
"num_return_sequences": 1,
|
| 191 |
+
"output_scores": false,
|
| 192 |
+
"return_dict_in_generate": false,
|
| 193 |
+
"forced_bos_token_id": null,
|
| 194 |
+
"forced_eos_token_id": null,
|
| 195 |
+
"remove_invalid_values": false,
|
| 196 |
+
"exponential_decay_length_penalty": null,
|
| 197 |
+
"suppress_tokens": null,
|
| 198 |
+
"begin_suppress_tokens": null,
|
| 199 |
+
"architectures": null,
|
| 200 |
+
"finetuning_task": null,
|
| 201 |
+
"id2label": {
|
| 202 |
+
"0": "LABEL_0",
|
| 203 |
+
"1": "LABEL_1"
|
| 204 |
+
},
|
| 205 |
+
"label2id": {
|
| 206 |
+
"LABEL_0": 0,
|
| 207 |
+
"LABEL_1": 1
|
| 208 |
+
},
|
| 209 |
+
"tokenizer_class": null,
|
| 210 |
+
"prefix": null,
|
| 211 |
+
"bos_token_id": null,
|
| 212 |
+
"pad_token_id": null,
|
| 213 |
+
"eos_token_id": null,
|
| 214 |
+
"sep_token_id": null,
|
| 215 |
+
"decoder_start_token_id": null,
|
| 216 |
+
"task_specific_params": null,
|
| 217 |
+
"problem_type": null,
|
| 218 |
+
"_name_or_path": "",
|
| 219 |
+
"_attn_implementation_autoset": false,
|
| 220 |
"model_type": "siglip_vision_model",
|
| 221 |
+
"vision_use_head": false,
|
| 222 |
+
"hidden_size": 1152,
|
| 223 |
+
"intermediate_size": 4304,
|
| 224 |
"num_hidden_layers": 26,
|
| 225 |
+
"num_attention_heads": 16,
|
| 226 |
+
"num_channels": 3,
|
| 227 |
"patch_size": 14,
|
| 228 |
+
"image_size": 384,
|
| 229 |
+
"attention_dropout": 0.0,
|
| 230 |
+
"layer_norm_eps": 1e-06,
|
| 231 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 232 |
+
"skip_vision": true
|
| 233 |
},
|
| 234 |
"vision_feature_layer": -1,
|
| 235 |
"vision_feature_select_strategy": "full"
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "4.43.0.dev0"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:933b367f620584a1afff6616d8405a8de7b197bb360ff6087c858ef0a04ef9f8
|
| 3 |
+
size 1291176525
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.model.embed_tokens.biases": "model.safetensors",
|
|
@@ -641,736 +641,422 @@
|
|
| 641 |
"multi_modal_projector.linear_2.weight": "model.safetensors",
|
| 642 |
"vision_tower.vision_model.embeddings.patch_embedding.bias": "model.safetensors",
|
| 643 |
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model.safetensors",
|
| 644 |
-
"vision_tower.vision_model.embeddings.position_embedding.biases": "model.safetensors",
|
| 645 |
-
"vision_tower.vision_model.embeddings.position_embedding.scales": "model.safetensors",
|
| 646 |
"vision_tower.vision_model.embeddings.position_embedding.weight": "model.safetensors",
|
| 647 |
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
|
| 648 |
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
|
| 649 |
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
|
| 650 |
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
|
| 651 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
|
| 652 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.biases": "model.safetensors",
|
| 653 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.scales": "model.safetensors",
|
| 654 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
|
| 655 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
|
| 656 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.biases": "model.safetensors",
|
| 657 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.scales": "model.safetensors",
|
| 658 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
|
| 659 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
|
| 660 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 661 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 662 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 663 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
|
| 664 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.biases": "model.safetensors",
|
| 665 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.scales": "model.safetensors",
|
| 666 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
|
| 667 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
|
| 668 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 669 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 670 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 671 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
|
| 672 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 673 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 674 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 675 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
|
| 676 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
|
| 677 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
|
| 678 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
|
| 679 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
|
| 680 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.biases": "model.safetensors",
|
| 681 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.scales": "model.safetensors",
|
| 682 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
|
| 683 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
|
| 684 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.biases": "model.safetensors",
|
| 685 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.scales": "model.safetensors",
|
| 686 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
|
| 687 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
|
| 688 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 689 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 690 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 691 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
|
| 692 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.biases": "model.safetensors",
|
| 693 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.scales": "model.safetensors",
|
| 694 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
|
| 695 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
|
| 696 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 697 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 698 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 699 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
|
| 700 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 701 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 702 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 703 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
|
| 704 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
|
| 705 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
|
| 706 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
|
| 707 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
|
| 708 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.biases": "model.safetensors",
|
| 709 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.scales": "model.safetensors",
|
| 710 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
|
| 711 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
|
| 712 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.biases": "model.safetensors",
|
| 713 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.scales": "model.safetensors",
|
| 714 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
|
| 715 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
|
| 716 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 717 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 718 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 719 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
|
| 720 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.biases": "model.safetensors",
|
| 721 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.scales": "model.safetensors",
|
| 722 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
|
| 723 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
|
| 724 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 725 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 726 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 727 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
|
| 728 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 729 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 730 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 731 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
|
| 732 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
|
| 733 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
|
| 734 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
|
| 735 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
|
| 736 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.biases": "model.safetensors",
|
| 737 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.scales": "model.safetensors",
|
| 738 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
|
| 739 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
|
| 740 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.biases": "model.safetensors",
|
| 741 |
-
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.scales": "model.safetensors",
|
| 742 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
|
| 743 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
|
| 744 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 745 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 746 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 747 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
|
| 748 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.biases": "model.safetensors",
|
| 749 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.scales": "model.safetensors",
|
| 750 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
|
| 751 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
|
| 752 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 753 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 754 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 755 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
|
| 756 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 757 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 758 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 759 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model.safetensors",
|
| 760 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model.safetensors",
|
| 761 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model.safetensors",
|
| 762 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model.safetensors",
|
| 763 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model.safetensors",
|
| 764 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.biases": "model.safetensors",
|
| 765 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.scales": "model.safetensors",
|
| 766 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model.safetensors",
|
| 767 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model.safetensors",
|
| 768 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.biases": "model.safetensors",
|
| 769 |
-
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.scales": "model.safetensors",
|
| 770 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model.safetensors",
|
| 771 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model.safetensors",
|
| 772 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 773 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 774 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 775 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model.safetensors",
|
| 776 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.biases": "model.safetensors",
|
| 777 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.scales": "model.safetensors",
|
| 778 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model.safetensors",
|
| 779 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model.safetensors",
|
| 780 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 781 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 782 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 783 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model.safetensors",
|
| 784 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 785 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 786 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 787 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model.safetensors",
|
| 788 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model.safetensors",
|
| 789 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model.safetensors",
|
| 790 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model.safetensors",
|
| 791 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model.safetensors",
|
| 792 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.biases": "model.safetensors",
|
| 793 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.scales": "model.safetensors",
|
| 794 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model.safetensors",
|
| 795 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model.safetensors",
|
| 796 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.biases": "model.safetensors",
|
| 797 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.scales": "model.safetensors",
|
| 798 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model.safetensors",
|
| 799 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model.safetensors",
|
| 800 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 801 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 802 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 803 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model.safetensors",
|
| 804 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.biases": "model.safetensors",
|
| 805 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.scales": "model.safetensors",
|
| 806 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model.safetensors",
|
| 807 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model.safetensors",
|
| 808 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 809 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 810 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 811 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model.safetensors",
|
| 812 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 813 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 814 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 815 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model.safetensors",
|
| 816 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model.safetensors",
|
| 817 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model.safetensors",
|
| 818 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model.safetensors",
|
| 819 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model.safetensors",
|
| 820 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.biases": "model.safetensors",
|
| 821 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.scales": "model.safetensors",
|
| 822 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model.safetensors",
|
| 823 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model.safetensors",
|
| 824 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.biases": "model.safetensors",
|
| 825 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.scales": "model.safetensors",
|
| 826 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model.safetensors",
|
| 827 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model.safetensors",
|
| 828 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 829 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 830 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 831 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model.safetensors",
|
| 832 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.biases": "model.safetensors",
|
| 833 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.scales": "model.safetensors",
|
| 834 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model.safetensors",
|
| 835 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model.safetensors",
|
| 836 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 837 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 838 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 839 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model.safetensors",
|
| 840 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 841 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 842 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 843 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model.safetensors",
|
| 844 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model.safetensors",
|
| 845 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model.safetensors",
|
| 846 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model.safetensors",
|
| 847 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model.safetensors",
|
| 848 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.biases": "model.safetensors",
|
| 849 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.scales": "model.safetensors",
|
| 850 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model.safetensors",
|
| 851 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model.safetensors",
|
| 852 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.biases": "model.safetensors",
|
| 853 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.scales": "model.safetensors",
|
| 854 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model.safetensors",
|
| 855 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model.safetensors",
|
| 856 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 857 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 858 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 859 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model.safetensors",
|
| 860 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.biases": "model.safetensors",
|
| 861 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.scales": "model.safetensors",
|
| 862 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model.safetensors",
|
| 863 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model.safetensors",
|
| 864 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 865 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 866 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 867 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model.safetensors",
|
| 868 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 869 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 870 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 871 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model.safetensors",
|
| 872 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model.safetensors",
|
| 873 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model.safetensors",
|
| 874 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model.safetensors",
|
| 875 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model.safetensors",
|
| 876 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.biases": "model.safetensors",
|
| 877 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.scales": "model.safetensors",
|
| 878 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model.safetensors",
|
| 879 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model.safetensors",
|
| 880 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.biases": "model.safetensors",
|
| 881 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.scales": "model.safetensors",
|
| 882 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model.safetensors",
|
| 883 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model.safetensors",
|
| 884 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 885 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 886 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 887 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model.safetensors",
|
| 888 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.biases": "model.safetensors",
|
| 889 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.scales": "model.safetensors",
|
| 890 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model.safetensors",
|
| 891 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model.safetensors",
|
| 892 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 893 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 894 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 895 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model.safetensors",
|
| 896 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 897 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 898 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 899 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model.safetensors",
|
| 900 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model.safetensors",
|
| 901 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model.safetensors",
|
| 902 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model.safetensors",
|
| 903 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model.safetensors",
|
| 904 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.biases": "model.safetensors",
|
| 905 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.scales": "model.safetensors",
|
| 906 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model.safetensors",
|
| 907 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model.safetensors",
|
| 908 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.biases": "model.safetensors",
|
| 909 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.scales": "model.safetensors",
|
| 910 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model.safetensors",
|
| 911 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model.safetensors",
|
| 912 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 913 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 914 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 915 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model.safetensors",
|
| 916 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.biases": "model.safetensors",
|
| 917 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.scales": "model.safetensors",
|
| 918 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model.safetensors",
|
| 919 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model.safetensors",
|
| 920 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 921 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 922 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 923 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model.safetensors",
|
| 924 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 925 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 926 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 927 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model.safetensors",
|
| 928 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model.safetensors",
|
| 929 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model.safetensors",
|
| 930 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model.safetensors",
|
| 931 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model.safetensors",
|
| 932 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.biases": "model.safetensors",
|
| 933 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.scales": "model.safetensors",
|
| 934 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model.safetensors",
|
| 935 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model.safetensors",
|
| 936 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.biases": "model.safetensors",
|
| 937 |
-
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.scales": "model.safetensors",
|
| 938 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model.safetensors",
|
| 939 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model.safetensors",
|
| 940 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 941 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 942 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 943 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model.safetensors",
|
| 944 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.biases": "model.safetensors",
|
| 945 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.scales": "model.safetensors",
|
| 946 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model.safetensors",
|
| 947 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model.safetensors",
|
| 948 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 949 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 950 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 951 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model.safetensors",
|
| 952 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 953 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 954 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 955 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model.safetensors",
|
| 956 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model.safetensors",
|
| 957 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model.safetensors",
|
| 958 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model.safetensors",
|
| 959 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model.safetensors",
|
| 960 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.biases": "model.safetensors",
|
| 961 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.scales": "model.safetensors",
|
| 962 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model.safetensors",
|
| 963 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model.safetensors",
|
| 964 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.biases": "model.safetensors",
|
| 965 |
-
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.scales": "model.safetensors",
|
| 966 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model.safetensors",
|
| 967 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model.safetensors",
|
| 968 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 969 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 970 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 971 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model.safetensors",
|
| 972 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.biases": "model.safetensors",
|
| 973 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.scales": "model.safetensors",
|
| 974 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model.safetensors",
|
| 975 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model.safetensors",
|
| 976 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 977 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 978 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 979 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model.safetensors",
|
| 980 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 981 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 982 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 983 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
|
| 984 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
|
| 985 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
|
| 986 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
|
| 987 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
|
| 988 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.biases": "model.safetensors",
|
| 989 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.scales": "model.safetensors",
|
| 990 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
|
| 991 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
|
| 992 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.biases": "model.safetensors",
|
| 993 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.scales": "model.safetensors",
|
| 994 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
|
| 995 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
|
| 996 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 997 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 998 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 999 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
|
| 1000 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.biases": "model.safetensors",
|
| 1001 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.scales": "model.safetensors",
|
| 1002 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
|
| 1003 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
|
| 1004 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 1005 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 1006 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 1007 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
|
| 1008 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 1009 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 1010 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 1011 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model.safetensors",
|
| 1012 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model.safetensors",
|
| 1013 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model.safetensors",
|
| 1014 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model.safetensors",
|
| 1015 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model.safetensors",
|
| 1016 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.biases": "model.safetensors",
|
| 1017 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.scales": "model.safetensors",
|
| 1018 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model.safetensors",
|
| 1019 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model.safetensors",
|
| 1020 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.biases": "model.safetensors",
|
| 1021 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.scales": "model.safetensors",
|
| 1022 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model.safetensors",
|
| 1023 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model.safetensors",
|
| 1024 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 1025 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 1026 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 1027 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model.safetensors",
|
| 1028 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.biases": "model.safetensors",
|
| 1029 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.scales": "model.safetensors",
|
| 1030 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model.safetensors",
|
| 1031 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model.safetensors",
|
| 1032 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 1033 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 1034 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 1035 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model.safetensors",
|
| 1036 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 1037 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 1038 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 1039 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model.safetensors",
|
| 1040 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model.safetensors",
|
| 1041 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model.safetensors",
|
| 1042 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model.safetensors",
|
| 1043 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model.safetensors",
|
| 1044 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.biases": "model.safetensors",
|
| 1045 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.scales": "model.safetensors",
|
| 1046 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model.safetensors",
|
| 1047 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model.safetensors",
|
| 1048 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.biases": "model.safetensors",
|
| 1049 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.scales": "model.safetensors",
|
| 1050 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model.safetensors",
|
| 1051 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model.safetensors",
|
| 1052 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 1053 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 1054 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 1055 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model.safetensors",
|
| 1056 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.biases": "model.safetensors",
|
| 1057 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.scales": "model.safetensors",
|
| 1058 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model.safetensors",
|
| 1059 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model.safetensors",
|
| 1060 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 1061 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 1062 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 1063 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model.safetensors",
|
| 1064 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 1065 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 1066 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 1067 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model.safetensors",
|
| 1068 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model.safetensors",
|
| 1069 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model.safetensors",
|
| 1070 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model.safetensors",
|
| 1071 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model.safetensors",
|
| 1072 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.biases": "model.safetensors",
|
| 1073 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.scales": "model.safetensors",
|
| 1074 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model.safetensors",
|
| 1075 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model.safetensors",
|
| 1076 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.biases": "model.safetensors",
|
| 1077 |
-
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.scales": "model.safetensors",
|
| 1078 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model.safetensors",
|
| 1079 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model.safetensors",
|
| 1080 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 1081 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 1082 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 1083 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model.safetensors",
|
| 1084 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.biases": "model.safetensors",
|
| 1085 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.scales": "model.safetensors",
|
| 1086 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model.safetensors",
|
| 1087 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model.safetensors",
|
| 1088 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 1089 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 1090 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 1091 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model.safetensors",
|
| 1092 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 1093 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 1094 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 1095 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model.safetensors",
|
| 1096 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model.safetensors",
|
| 1097 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model.safetensors",
|
| 1098 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model.safetensors",
|
| 1099 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model.safetensors",
|
| 1100 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.biases": "model.safetensors",
|
| 1101 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.scales": "model.safetensors",
|
| 1102 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model.safetensors",
|
| 1103 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model.safetensors",
|
| 1104 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.biases": "model.safetensors",
|
| 1105 |
-
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.scales": "model.safetensors",
|
| 1106 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model.safetensors",
|
| 1107 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model.safetensors",
|
| 1108 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 1109 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 1110 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 1111 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model.safetensors",
|
| 1112 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.biases": "model.safetensors",
|
| 1113 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.scales": "model.safetensors",
|
| 1114 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model.safetensors",
|
| 1115 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model.safetensors",
|
| 1116 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 1117 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 1118 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 1119 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model.safetensors",
|
| 1120 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 1121 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 1122 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 1123 |
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model.safetensors",
|
| 1124 |
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model.safetensors",
|
| 1125 |
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model.safetensors",
|
| 1126 |
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model.safetensors",
|
| 1127 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model.safetensors",
|
| 1128 |
-
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.biases": "model.safetensors",
|
| 1129 |
-
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.scales": "model.safetensors",
|
| 1130 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model.safetensors",
|
| 1131 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model.safetensors",
|
| 1132 |
-
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.biases": "model.safetensors",
|
| 1133 |
-
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.scales": "model.safetensors",
|
| 1134 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model.safetensors",
|
| 1135 |
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model.safetensors",
|
| 1136 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 1137 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 1138 |
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 1139 |
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model.safetensors",
|
| 1140 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.biases": "model.safetensors",
|
| 1141 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.scales": "model.safetensors",
|
| 1142 |
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model.safetensors",
|
| 1143 |
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model.safetensors",
|
| 1144 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 1145 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 1146 |
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 1147 |
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model.safetensors",
|
| 1148 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 1149 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 1150 |
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 1151 |
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model.safetensors",
|
| 1152 |
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model.safetensors",
|
| 1153 |
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model.safetensors",
|
| 1154 |
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model.safetensors",
|
| 1155 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model.safetensors",
|
| 1156 |
-
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.biases": "model.safetensors",
|
| 1157 |
-
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.scales": "model.safetensors",
|
| 1158 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model.safetensors",
|
| 1159 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model.safetensors",
|
| 1160 |
-
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.biases": "model.safetensors",
|
| 1161 |
-
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.scales": "model.safetensors",
|
| 1162 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model.safetensors",
|
| 1163 |
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model.safetensors",
|
| 1164 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 1165 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 1166 |
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 1167 |
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model.safetensors",
|
| 1168 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.biases": "model.safetensors",
|
| 1169 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.scales": "model.safetensors",
|
| 1170 |
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model.safetensors",
|
| 1171 |
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model.safetensors",
|
| 1172 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 1173 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 1174 |
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 1175 |
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model.safetensors",
|
| 1176 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 1177 |
-
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 1178 |
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 1179 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
|
| 1180 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
|
| 1181 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
|
| 1182 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
|
| 1183 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
|
| 1184 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.biases": "model.safetensors",
|
| 1185 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.scales": "model.safetensors",
|
| 1186 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
|
| 1187 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
|
| 1188 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.biases": "model.safetensors",
|
| 1189 |
-
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.scales": "model.safetensors",
|
| 1190 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
|
| 1191 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
|
| 1192 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 1193 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 1194 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 1195 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
|
| 1196 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.biases": "model.safetensors",
|
| 1197 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.scales": "model.safetensors",
|
| 1198 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
|
| 1199 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
|
| 1200 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 1201 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 1202 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 1203 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
|
| 1204 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 1205 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 1206 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 1207 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
|
| 1208 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
|
| 1209 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
|
| 1210 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
|
| 1211 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
|
| 1212 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.biases": "model.safetensors",
|
| 1213 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.scales": "model.safetensors",
|
| 1214 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
|
| 1215 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
|
| 1216 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.biases": "model.safetensors",
|
| 1217 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.scales": "model.safetensors",
|
| 1218 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
|
| 1219 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
|
| 1220 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 1221 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 1222 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 1223 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
|
| 1224 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.biases": "model.safetensors",
|
| 1225 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.scales": "model.safetensors",
|
| 1226 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
|
| 1227 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
|
| 1228 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 1229 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 1230 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 1231 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
|
| 1232 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 1233 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 1234 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 1235 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
|
| 1236 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
|
| 1237 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
|
| 1238 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
|
| 1239 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
|
| 1240 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.biases": "model.safetensors",
|
| 1241 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.scales": "model.safetensors",
|
| 1242 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
|
| 1243 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
|
| 1244 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.biases": "model.safetensors",
|
| 1245 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.scales": "model.safetensors",
|
| 1246 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
|
| 1247 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
|
| 1248 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 1249 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 1250 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 1251 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
|
| 1252 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.biases": "model.safetensors",
|
| 1253 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.scales": "model.safetensors",
|
| 1254 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
|
| 1255 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
|
| 1256 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 1257 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 1258 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 1259 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
|
| 1260 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 1261 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 1262 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 1263 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
|
| 1264 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
|
| 1265 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
|
| 1266 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
|
| 1267 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
|
| 1268 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.biases": "model.safetensors",
|
| 1269 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.scales": "model.safetensors",
|
| 1270 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
|
| 1271 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
|
| 1272 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.biases": "model.safetensors",
|
| 1273 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.scales": "model.safetensors",
|
| 1274 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
|
| 1275 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
|
| 1276 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 1277 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 1278 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 1279 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
|
| 1280 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.biases": "model.safetensors",
|
| 1281 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.scales": "model.safetensors",
|
| 1282 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
|
| 1283 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
|
| 1284 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 1285 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 1286 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 1287 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
|
| 1288 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 1289 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 1290 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 1291 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
|
| 1292 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
|
| 1293 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
|
| 1294 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
|
| 1295 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
|
| 1296 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.biases": "model.safetensors",
|
| 1297 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.scales": "model.safetensors",
|
| 1298 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
|
| 1299 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
|
| 1300 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.biases": "model.safetensors",
|
| 1301 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.scales": "model.safetensors",
|
| 1302 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
|
| 1303 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
|
| 1304 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 1305 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 1306 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 1307 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
|
| 1308 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.biases": "model.safetensors",
|
| 1309 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.scales": "model.safetensors",
|
| 1310 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
|
| 1311 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
|
| 1312 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 1313 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 1314 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 1315 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
|
| 1316 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 1317 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 1318 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 1319 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
|
| 1320 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
|
| 1321 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
|
| 1322 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
|
| 1323 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
|
| 1324 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.biases": "model.safetensors",
|
| 1325 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.scales": "model.safetensors",
|
| 1326 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
|
| 1327 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
|
| 1328 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.biases": "model.safetensors",
|
| 1329 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.scales": "model.safetensors",
|
| 1330 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
|
| 1331 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
|
| 1332 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 1333 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 1334 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 1335 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
|
| 1336 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.biases": "model.safetensors",
|
| 1337 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.scales": "model.safetensors",
|
| 1338 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
|
| 1339 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
|
| 1340 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 1341 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 1342 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 1343 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
|
| 1344 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 1345 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 1346 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 1347 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
|
| 1348 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
|
| 1349 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
|
| 1350 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
|
| 1351 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
|
| 1352 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.biases": "model.safetensors",
|
| 1353 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.scales": "model.safetensors",
|
| 1354 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
|
| 1355 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
|
| 1356 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.biases": "model.safetensors",
|
| 1357 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.scales": "model.safetensors",
|
| 1358 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
|
| 1359 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
|
| 1360 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 1361 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 1362 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 1363 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
|
| 1364 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.biases": "model.safetensors",
|
| 1365 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.scales": "model.safetensors",
|
| 1366 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
|
| 1367 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
|
| 1368 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 1369 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 1370 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 1371 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
|
| 1372 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 1373 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 1374 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 1375 |
"vision_tower.vision_model.post_layernorm.bias": "model.safetensors",
|
| 1376 |
"vision_tower.vision_model.post_layernorm.weight": "model.safetensors"
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 1291039808
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.model.embed_tokens.biases": "model.safetensors",
|
|
|
|
| 641 |
"multi_modal_projector.linear_2.weight": "model.safetensors",
|
| 642 |
"vision_tower.vision_model.embeddings.patch_embedding.bias": "model.safetensors",
|
| 643 |
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model.safetensors",
|
|
|
|
|
|
|
| 644 |
"vision_tower.vision_model.embeddings.position_embedding.weight": "model.safetensors",
|
| 645 |
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
|
| 646 |
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
|
| 647 |
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
|
| 648 |
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
|
| 649 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 650 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
|
| 651 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 652 |
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
|
| 653 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 654 |
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 655 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 656 |
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
|
| 657 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 658 |
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 659 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 660 |
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 661 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
|
| 662 |
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
|
| 663 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
|
| 664 |
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
|
| 665 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 666 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
|
| 667 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 668 |
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
|
| 669 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 670 |
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 671 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 672 |
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
|
| 673 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 674 |
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 675 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 676 |
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 677 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
|
| 678 |
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
|
| 679 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
|
| 680 |
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
|
| 681 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 682 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
|
| 683 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 684 |
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
|
| 685 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 686 |
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 687 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 688 |
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
|
| 689 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 690 |
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 691 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 692 |
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 693 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
|
| 694 |
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
|
| 695 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
|
| 696 |
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
|
| 697 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 698 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
|
| 699 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 700 |
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
|
| 701 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 702 |
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 703 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 704 |
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
|
| 705 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 706 |
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 707 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 708 |
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 709 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model.safetensors",
|
| 710 |
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model.safetensors",
|
| 711 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model.safetensors",
|
| 712 |
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model.safetensors",
|
| 713 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 714 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model.safetensors",
|
| 715 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 716 |
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model.safetensors",
|
| 717 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 718 |
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 719 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 720 |
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model.safetensors",
|
| 721 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 722 |
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 723 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 724 |
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 725 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model.safetensors",
|
| 726 |
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model.safetensors",
|
| 727 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model.safetensors",
|
| 728 |
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model.safetensors",
|
| 729 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 730 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model.safetensors",
|
| 731 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 732 |
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model.safetensors",
|
| 733 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 734 |
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 735 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 736 |
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model.safetensors",
|
| 737 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 738 |
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 739 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 740 |
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 741 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model.safetensors",
|
| 742 |
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model.safetensors",
|
| 743 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model.safetensors",
|
| 744 |
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model.safetensors",
|
| 745 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 746 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model.safetensors",
|
| 747 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 748 |
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model.safetensors",
|
| 749 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 750 |
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 751 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 752 |
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model.safetensors",
|
| 753 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 754 |
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 755 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 756 |
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 757 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model.safetensors",
|
| 758 |
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model.safetensors",
|
| 759 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model.safetensors",
|
| 760 |
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model.safetensors",
|
| 761 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 762 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model.safetensors",
|
| 763 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 764 |
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model.safetensors",
|
| 765 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 766 |
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 767 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 768 |
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model.safetensors",
|
| 769 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 770 |
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 771 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 772 |
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 773 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model.safetensors",
|
| 774 |
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model.safetensors",
|
| 775 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model.safetensors",
|
| 776 |
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model.safetensors",
|
| 777 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 778 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model.safetensors",
|
| 779 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 780 |
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model.safetensors",
|
| 781 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 782 |
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 783 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 784 |
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model.safetensors",
|
| 785 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 786 |
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 787 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 788 |
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 789 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model.safetensors",
|
| 790 |
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model.safetensors",
|
| 791 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model.safetensors",
|
| 792 |
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model.safetensors",
|
| 793 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 794 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model.safetensors",
|
| 795 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 796 |
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model.safetensors",
|
| 797 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 798 |
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 799 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 800 |
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model.safetensors",
|
| 801 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 802 |
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 803 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 804 |
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 805 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model.safetensors",
|
| 806 |
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model.safetensors",
|
| 807 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model.safetensors",
|
| 808 |
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model.safetensors",
|
| 809 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 810 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model.safetensors",
|
| 811 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 812 |
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model.safetensors",
|
| 813 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 814 |
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 815 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 816 |
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model.safetensors",
|
| 817 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 818 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 819 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 820 |
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 821 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model.safetensors",
|
| 822 |
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model.safetensors",
|
| 823 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model.safetensors",
|
| 824 |
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model.safetensors",
|
| 825 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 826 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model.safetensors",
|
| 827 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 828 |
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model.safetensors",
|
| 829 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 830 |
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 831 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 832 |
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model.safetensors",
|
| 833 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 834 |
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 835 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 836 |
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 837 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
|
| 838 |
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
|
| 839 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
|
| 840 |
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
|
| 841 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 842 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
|
| 843 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 844 |
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
|
| 845 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 846 |
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 847 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 848 |
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
|
| 849 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 850 |
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 851 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 852 |
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 853 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model.safetensors",
|
| 854 |
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model.safetensors",
|
| 855 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model.safetensors",
|
| 856 |
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model.safetensors",
|
| 857 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 858 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model.safetensors",
|
| 859 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 860 |
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model.safetensors",
|
| 861 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 862 |
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 863 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 864 |
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model.safetensors",
|
| 865 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 866 |
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 867 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 868 |
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 869 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model.safetensors",
|
| 870 |
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model.safetensors",
|
| 871 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model.safetensors",
|
| 872 |
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model.safetensors",
|
| 873 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 874 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model.safetensors",
|
| 875 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 876 |
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model.safetensors",
|
| 877 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 878 |
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 879 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 880 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model.safetensors",
|
| 881 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 882 |
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 883 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 884 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 885 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model.safetensors",
|
| 886 |
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model.safetensors",
|
| 887 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model.safetensors",
|
| 888 |
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model.safetensors",
|
| 889 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 890 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model.safetensors",
|
| 891 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 892 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model.safetensors",
|
| 893 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 894 |
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 895 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 896 |
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model.safetensors",
|
| 897 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 898 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 899 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 900 |
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 901 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model.safetensors",
|
| 902 |
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model.safetensors",
|
| 903 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model.safetensors",
|
| 904 |
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model.safetensors",
|
| 905 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 906 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model.safetensors",
|
| 907 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 908 |
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model.safetensors",
|
| 909 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 910 |
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 911 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 912 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model.safetensors",
|
| 913 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 914 |
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 915 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 916 |
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 917 |
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model.safetensors",
|
| 918 |
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model.safetensors",
|
| 919 |
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model.safetensors",
|
| 920 |
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model.safetensors",
|
| 921 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 922 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model.safetensors",
|
| 923 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 924 |
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model.safetensors",
|
| 925 |
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 926 |
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 927 |
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 928 |
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model.safetensors",
|
| 929 |
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 930 |
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 931 |
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 932 |
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 933 |
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model.safetensors",
|
| 934 |
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model.safetensors",
|
| 935 |
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model.safetensors",
|
| 936 |
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model.safetensors",
|
| 937 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 938 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model.safetensors",
|
| 939 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 940 |
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model.safetensors",
|
| 941 |
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 942 |
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 943 |
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 944 |
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model.safetensors",
|
| 945 |
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 946 |
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 947 |
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 948 |
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 949 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
|
| 950 |
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
|
| 951 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
|
| 952 |
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
|
| 953 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 954 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
|
| 955 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 956 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
|
| 957 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 958 |
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 959 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 960 |
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
|
| 961 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 962 |
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 963 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 964 |
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 965 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
|
| 966 |
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
|
| 967 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
|
| 968 |
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
|
| 969 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 970 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
|
| 971 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 972 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
|
| 973 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 974 |
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 975 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 976 |
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
|
| 977 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 978 |
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 979 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 980 |
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 981 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
|
| 982 |
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
|
| 983 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
|
| 984 |
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
|
| 985 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 986 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
|
| 987 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 988 |
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
|
| 989 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 990 |
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 991 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 992 |
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
|
| 993 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 994 |
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 995 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 996 |
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 997 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
|
| 998 |
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
|
| 999 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
|
| 1000 |
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
|
| 1001 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1002 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
|
| 1003 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1004 |
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
|
| 1005 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1006 |
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 1007 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1008 |
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
|
| 1009 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1010 |
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 1011 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1012 |
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 1013 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
|
| 1014 |
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
|
| 1015 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
|
| 1016 |
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
|
| 1017 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1018 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
|
| 1019 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1020 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
|
| 1021 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1022 |
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 1023 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1024 |
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
|
| 1025 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1026 |
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 1027 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1028 |
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 1029 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
|
| 1030 |
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
|
| 1031 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
|
| 1032 |
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
|
| 1033 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1034 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
|
| 1035 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1036 |
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
|
| 1037 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1038 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 1039 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1040 |
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
|
| 1041 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1042 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 1043 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1044 |
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 1045 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
|
| 1046 |
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
|
| 1047 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
|
| 1048 |
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
|
| 1049 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1050 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
|
| 1051 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1052 |
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
|
| 1053 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1054 |
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 1055 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1056 |
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
|
| 1057 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1058 |
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 1059 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
|
|
|
|
|
|
|
| 1060 |
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 1061 |
"vision_tower.vision_model.post_layernorm.bias": "model.safetensors",
|
| 1062 |
"vision_tower.vision_model.post_layernorm.weight": "model.safetensors"
|
processor_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"image_token": "<image>",
|
| 3 |
-
"
|
|
|
|
| 4 |
"processor_class": "LlavaProcessor",
|
| 5 |
-
"vision_feature_select_strategy":
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"image_token": "<image>",
|
| 3 |
+
"num_additional_image_tokens": 0,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
"processor_class": "LlavaProcessor",
|
| 6 |
+
"vision_feature_select_strategy": "full"
|
| 7 |
}
|
special_tokens_map.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
|
|
|
| 13 |
"pad_token": {
|
| 14 |
"content": "<|endoftext|>",
|
| 15 |
"lstrip": false,
|
|
|
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
+
"image_token": "<image>",
|
| 14 |
"pad_token": {
|
| 15 |
"content": "<|endoftext|>",
|
| 16 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -43,6 +43,10 @@
|
|
| 43 |
"clean_up_tokenization_spaces": false,
|
| 44 |
"eos_token": "<|im_end|>",
|
| 45 |
"errors": "replace",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"model_max_length": 32768,
|
| 47 |
"pad_token": "<|endoftext|>",
|
| 48 |
"processor_class": "LlavaProcessor",
|
|
|
|
| 43 |
"clean_up_tokenization_spaces": false,
|
| 44 |
"eos_token": "<|im_end|>",
|
| 45 |
"errors": "replace",
|
| 46 |
+
"extra_special_tokens": {
|
| 47 |
+
"image_token": "<image>"
|
| 48 |
+
},
|
| 49 |
+
"image_token": "<image>",
|
| 50 |
"model_max_length": 32768,
|
| 51 |
"pad_token": "<|endoftext|>",
|
| 52 |
"processor_class": "LlavaProcessor",
|