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
+processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "adept/fuyu-8b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h",
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d56d57a0beffff58437a21f9546989efef65fc9dcc8b6cb270246bea8d6713
+size 75541088

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "adept/fuyu-8b",
+  "architectures": [
+    "FuyuForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 71013,
+  "hidden_act": "relu2",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "image_size": 300,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 16384,
+  "model_type": "fuyu",
+  "num_attention_heads": 64,
+  "num_channels": 3,
+  "num_hidden_layers": 36,
+  "partial_rotary_factor": 0.5,
+  "patch_size": 30,
+  "qk_layernorm": true,
+  "rope_scaling": null,
+  "rope_theta": 25000.0,
+  "text_config": {
+    "model_type": "persimmon"
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 71013,
+  "transformers_version": "4.36.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900fc4a31aa9a5f5a8bf25fe5d6ab8413ac709ebd6cbedf9f679f0b8083492d2
+size 4966819760

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc25bd174fdb2dd0e604c4016da216935f8ae2aec683f26c9e23618d7712c6b
+size 4967399488

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72659f06991ee22f0f47d82f1c071bd7e3d97ed9ae7c13ff16dd1ec4d33af6e
+size 4967398232

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa25955b10ab744332823f720d533388dea2afcdfccffcc082be11809685ba6
+size 3914935856

model.safetensors.index.json

@@ -0,0 +1,589 @@
+{
+  "metadata": {
+    "total_size": 18816477184
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.final_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.final_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.32.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.dense.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.dense.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.32.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.dense.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.dense.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.33.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.dense.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.dense.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.34.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.dense.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.dense.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.35.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "vision_embed_tokens.bias": "model-00004-of-00004.safetensors",
+    "vision_embed_tokens.weight": "model-00004-of-00004.safetensors"
+  }
+}

processor/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": 0.5,
+  "image_processor_type": "FuyuImageProcessor",
+  "image_std": 0.5,
+  "padding_mode": "constant",
+  "padding_value": 1.0,
+  "patch_size": {
+    "height": 30,
+    "width": 30
+  },
+  "processor_class": "FuyuProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1080,
+    "width": 1920
+  },
+  "target_height": 1080,
+  "target_width": 1920
+}

processor/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "|ENDOFTEXT|"
+  ],
+  "bos_token": {
+    "content": "|ENDOFTEXT|",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "|ENDOFTEXT|",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

processor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20119416a890c3fefc86210999fb8189dde194c12f7f861dbb3bc7a922baaabb
+size 16454569

processor/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407d001d18582959881b30ff39b660d4bd5ee50957d03f57daeeb3059e9db54c
+size 6128796

processor/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71013": {
+      "content": "|ENDOFTEXT|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "|ENDOFTEXT|"
+  ],
+  "bos_token": "|ENDOFTEXT|",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "|ENDOFTEXT|",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "processor_class": "FuyuProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}