Duplicate from MFuyu/mfuyu_1.5_8b_8192_720p

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,58 @@
+---
+license: cc-by-nc-4.0
+base_model: adept/fuyu-8b
+tags:
+- generated_from_trainer
+model-index:
+- name: mfuyu_1.5_8b_8192_720p
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mfuyu_1.5_8b_8192_720p
+
+This model is a fine-tuned version of [adept/fuyu-8b](https://huggingface.co/adept/fuyu-8b) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "adept/fuyu-8b",
+  "architectures": [
+    "MFuyuForCausalLM"
+  ],
+  "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",
+    "vocab_size": 262146
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 262146
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 71013,
+  "transformers_version": "4.39.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0acf81d38756c5eaeb73e2f370bf1a79c054c21f6a8addcd4b22ace654366198
+size 4966836144

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bba3efd375033ebc27bb847a1a3c11d15d5b756437fd5d3d13518e67bca0587
+size 4967399488

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b378331344f472fe0f165e7d3ab37c0ab36c526afb8f8f0b91f7f76de4924d
+size 4967398232

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa5685585766cf6ec6472ac7d94c8fe1d97fcaa7ca525459ee9e1bb3986b024
+size 3914952240

model.safetensors.index.json

@@ -0,0 +1,589 @@
+{
+  "metadata": {
+    "total_size": 18816509952
+  },
+  "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"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_pad",
+    "padding_value",
+    "padding_mode",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_rescale",
+    "rescale_factor",
+    "patch_size",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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": "MFuyuProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 720,
+    "width": 1290
+  },
+  "target_height": 1080,
+  "target_width": 1920
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "|IMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "|ENDOFIMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6db0b2169918176bbed18b26e73d12d8c09dfa0ed8b248d2c054e7df9f5cfce
+size 16454942

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "262144": {
+      "content": "|IMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262145": {
+      "content": "|ENDOFIMAGE|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "|IMAGE|",
+    "|ENDOFIMAGE|"
+  ],
+  "bos_token": "|ENDOFTEXT|",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "|ENDOFTEXT|",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "processor_class": "MFuyuProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36dccf48cf96f5e3d58636b7cde1d7b87f024c4257141bdd6711617b0690c65
+size 6264