Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# GLM-Mag
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the Passthrough merge method using /home/quixi/storage/models/GLM-Tulu + /home/quixi/storage/models/Rei-SFT-Lora as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: /home/quixi/storage/models/GLM-Tulu+/home/quixi/storage/models/Rei-SFT-Lora
+dtype: bfloat16
+merge_method: passthrough
+models:
+  - model: /home/quixi/storage/models/GLM-Tulu+/home/quixi/storage/models/Rei-SFT-Lora
+
+```

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Glm4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151343,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "model_type": "glm4",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 151345
+}

mergekit_config.yml

@@ -0,0 +1,5 @@
+base_model: /home/quixi/storage/models/GLM-Tulu+/home/quixi/storage/models/Rei-SFT-Lora
+dtype: bfloat16
+merge_method: passthrough
+models:
+  - model: /home/quixi/storage/models/GLM-Tulu+/home/quixi/storage/models/Rei-SFT-Lora

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c87b8d7ebf09a17326af2457ffa2ad33658dcf62557812f0ab44cedc4fed64
+size 4726150632

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc3f799036608ba1a35053b78d8753ab5dc92fbcb8a6062db8213ab7b2ac6c1
+size 4954760608

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b37eeefbf8bf8339c2e3aa0c94a244fb774fbe0f59d3af3e317921d5ae920d6
+size 4957918848

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24780b6ff5c3b6b8ff1a1042ff82c63b032063f45ba2f3b78cd6f1a7e122965b
+size 4464002216

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfbf92e624994b0114a001892011b09191089b78a94cafffb817392f6ebae38e
+size 4750300808

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aec20a05df5cb73d9cd5808f1b04a666ea44d9ca86646ac715d73386974205
+size 4954760608

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bc2cbba09745dd23bc2977409011c5bee4190de1eb9e1aa0b1e5c3c8cb5bff
+size 4957918848

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e86ac0d12afe2260d4529726a9f8f5cfb295ca8760a75681c43e9c6e61efda
+size 4464002224

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36201a66c4b60be2cddd4d863b8c8775924b8664f8cb7ab5e525c2d25261248
+size 4750300800

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4765068a78fad2faad69fcecaa155342f74099557f537ab29e7179159bc62a
+size 4954760616

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9078d5996e0da21352a342edfcbc4c6ce610a12a7b8da3a1d518dbb187a50e8
+size 4957918840

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352d3b06a74dbfe21a36fa1d4865ace4ecfdc2bfeee8cf92894789a0d27a038d
+size 4464002224

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6142485d54fffdc1e816ac8752acf3dcb34f972886231138152bcf77b30640e
+size 4750300800

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57997255ae102b0bc7c8eff9bf741917898789783f6c26d9bd47c1fd3c9b4664
+size 3020049832

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373d3e2e65cc5e215af93845ef1f79d849095ee1428047c2909814e297bc2d33
+size 19966873

tokenizer_config.json

@@ -0,0 +1,161 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}