Model save

README.md

@@ -0,0 +1,58 @@
+---
+license: cc-by-nc-4.0
+base_model: MFuyu/mfuyu_llava_8192_480p
+tags:
+- generated_from_trainer
+model-index:
+- name: mfuyu_llava_nlvr2_lrv_8192_480p
+  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_llava_nlvr2_lrv_8192_480p
+
+This model is a fine-tuned version of [MFuyu/mfuyu_llava_8192_480p](https://huggingface.co/MFuyu/mfuyu_llava_8192_480p) 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: 4
+- total_train_batch_size: 64
+- 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 71013,
+  "transformers_version": "4.37.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61214094dc12d1f5081c04a0ddea897cf034c850d0c783c6c72805c7c0384ab
+size 4966836144

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe60f61a5cd7cc580d04f026ea8107c927cae60ee428cc74ebbbb751034ff507
+size 4967399488

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4b32aa95fe3406965925694b0c1c2605b94376ed621a8326ab5534c4630a18
+size 4967398232

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a5c8bb9c23828e706614e4b074cfa8851790e64b24a116e0ab0913bdd297be
+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"
+  }
+}