Add initial model files

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "LLM360/CrystalChat",
+  "activation_function": "swiglu",
+  "architectures": [
+    "LlavaCrystalForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "LLM360/CrystalChat--configuration_crystalcoder.CrystalCoderConfig",
+    "AutoModel": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderModel",
+    "AutoModelForCausalLM": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderLMHeadModel"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "mm_hidden_size": 1024,
+  "mm_patch_num": 576,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_crystal",
+  "mup_embeddings_scale": 14.6,
+  "mup_output_alpha": 2.22,
+  "mup_scale_qk_dot_by_d": true,
+  "mup_width_scale": 0.0625,
+  "n_embd": 4096,
+  "n_head": 32,
+  "n_inner": 10922,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "position_embedding_type": "rotary",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32032
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0566431a4cc3e74fe974a1620e8f3a5e877c6e3ec83f63697de3702d2b22cf
+size 9928636172

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a78c24a5bfda7b04797d4a2418e8994f7fd4342daa2e8b378c405c0db0b118
+size 3871196172

pytorch_model.bin.index.json

@@ -0,0 +1,854 @@
+{
+  "metadata": {
+    "total_size": 13799531776
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|filename|>",
+    "<|gh_stars|>",
+    "<|issue_start|>",
+    "<|issue_comment|>",
+    "<|issue_closed|>",
+    "<|jupyter_start|>",
+    "<|jupyter_text|>",
+    "<|jupyter_code|>",
+    "<|jupyter_output|>",
+    "<|empty_output|>",
+    "<|commit_before|>",
+    "<|commit_msg|>",
+    "<|commit_after|>",
+    "<|reponame|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|sys_start|>",
+    "<|sys_end|>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenization_crystalcoder_fast.py

@@ -0,0 +1,144 @@
+
+import os
+from shutil import copyfile
+from typing import Optional, Tuple
+
+from tokenizers import processors
+
+from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
+from transformers.utils import is_sentencepiece_available, logging
+from transformers.utils.versions import require_version
+
+
+require_version("tokenizers>=0.13.3")
+
+
+
+logger = logging.get_logger(__name__)
+VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model", "tokenizer_file": "tokenizer.json"}
+
+# fmt: off
+DEFAULT_SYSTEM_PROMPT = """You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your \
+answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure\
+ that your responses are socially unbiased and positive in nature.
+
+If a question does not make any sense, or is not factually coherent, explain why instead of answering something not \
+correct. If you don't know the answer to a question, please don't share false information."""
+# fmt: on
+
+
+class CrystalCoderTokenizerFast(PreTrainedTokenizerFast):
+    
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    slow_tokenizer_class = None
+    padding_side = "left"
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file=None,
+        tokenizer_file=None,
+        clean_up_tokenization_spaces=False,
+        unk_token="<|unk|>",
+        bos_token="<|startoftext|>",
+        eos_token="<|endoftext|>",
+        add_bos_token=False,
+        add_eos_token=False,
+        use_default_system_prompt=False,
+        **kwargs,
+    ):
+        super().__init__(
+            vocab_file=vocab_file,
+            tokenizer_file=tokenizer_file,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            unk_token=unk_token,
+            bos_token=bos_token,
+            eos_token=eos_token,
+            use_default_system_prompt=use_default_system_prompt,
+            **kwargs,
+        )
+        self._add_bos_token = add_bos_token
+        self._add_eos_token = add_eos_token
+        self.update_post_processor()
+        self.use_default_system_prompt = use_default_system_prompt
+        self.vocab_file = vocab_file
+
+    @property
+    def can_save_slow_tokenizer(self) -> bool:
+        return os.path.isfile(self.vocab_file) if self.vocab_file else False
+
+    def update_post_processor(self):
+        """
+        Updates the underlying post processor with the current `bos_token` and `eos_token`.
+        """
+        bos = self.bos_token
+        bos_token_id = self.bos_token_id
+        if bos is None and self.add_bos_token:
+            raise ValueError("add_bos_token = True but bos_token = None")
+
+        eos = self.eos_token
+        eos_token_id = self.eos_token_id
+        if eos is None and self.add_eos_token:
+            raise ValueError("add_eos_token = True but eos_token = None")
+
+        single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
+        pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
+
+        special_tokens = []
+        if self.add_bos_token:
+            special_tokens.append((bos, bos_token_id))
+        if self.add_eos_token:
+            special_tokens.append((eos, eos_token_id))
+        self._tokenizer.post_processor = processors.TemplateProcessing(
+            single=single, pair=pair, special_tokens=special_tokens
+        )
+
+    @property
+    def add_eos_token(self):
+        return self._add_eos_token
+
+    @property
+    def add_bos_token(self):
+        return self._add_bos_token
+
+    @add_eos_token.setter
+    def add_eos_token(self, value):
+        self._add_eos_token = value
+        self.update_post_processor()
+
+    @add_bos_token.setter
+    def add_bos_token(self, value):
+        self._add_bos_token = value
+        self.update_post_processor()
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        if not self.can_save_slow_tokenizer:
+            raise ValueError(
+                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
+                "tokenizer."
+            )
+
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+
+        return (out_vocab_file,)
+
+
+    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = bos_token_id + token_ids_0 + eos_token_id
+
+        if token_ids_1 is not None:
+            output = output + bos_token_id + token_ids_1 + eos_token_id
+
+        return output

tokenizer_config.json

@@ -0,0 +1,269 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|filename|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|gh_stars|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|issue_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|issue_comment|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|issue_closed|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|jupyter_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|jupyter_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<|jupyter_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<|jupyter_output|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<|empty_output|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<|commit_before|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<|commit_msg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<|commit_after|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<|reponame|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<|sys_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<|sys_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<|filename|>",
+    "<|gh_stars|>",
+    "<|issue_start|>",
+    "<|issue_comment|>",
+    "<|issue_closed|>",
+    "<|jupyter_start|>",
+    "<|jupyter_text|>",
+    "<|jupyter_code|>",
+    "<|jupyter_output|>",
+    "<|empty_output|>",
+    "<|commit_before|>",
+    "<|commit_msg|>",
+    "<|commit_after|>",
+    "<|reponame|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|sys_start|>",
+    "<|sys_end|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      null,
+      "tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CrystalCoderTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d652a95a91094e3330f9a1d196a763a4e9506de3082f6f155ef81b2dca79efd
+size 6011