Training in progress, epoch 1

.gitattributes

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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: zai-org/GLM-4.1V-9B-Thinking
+library_name: transformers
+model_name: geom3k_CoT_sft_5e5_lora
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for geom3k_CoT_sft_5e5_lora
+
+This model is a fine-tuned version of [zai-org/GLM-4.1V-9B-Thinking](https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="amazingvince/geom3k_CoT_sft_5e5_lora", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/amazingvince/huggingface/runs/fvemhlx6) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.22.2
+- Transformers: 4.56.1
+- Pytorch: 2.8.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4.1V-9B-Thinking",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "merger.proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "gate_up_proj",
+    "qkv",
+    "k_proj",
+    "attn.proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23df0a32587f3eb31b33775862d62c25584467aaeefd82d60b02eed6ac713ae4
+size 117320232

chat_template.jinja

@@ -0,0 +1,33 @@
+[gMASK]<sop>
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- elif msg.role == 'user' %}
+<|user|>{{ '\n' }}
+
+        {%- if msg.content is string %}
+{{ msg.content }}
+        {%- else %}
+            {%- for item in msg.content %}
+                {%- if item.type == 'video' or 'video' in item %}
+<|begin_of_video|><|video|><|end_of_video|>
+                {%- elif item.type == 'image' or 'image' in item %}
+<|begin_of_image|><|image|><|end_of_image|>
+                {%- elif item.type == 'text' %}
+{{ item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- elif msg.role == 'assistant' %}
+        {%- if msg.metadata %}
+<|assistant|>{{ msg.metadata }}
+{{ msg.content }}
+        {%- else %}
+<|assistant|>
+{{ msg.content }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>
+{% endif %}

config.json

@@ -0,0 +1,101 @@
+{
+  "architectures": [
+    "Glm4vForConditionalGeneration"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151329,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_end_token_id": 151340,
+  "image_start_token_id": 151339,
+  "image_token_id": 151343,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "max_position_embeddings": 65536,
+  "model_type": "glm4v",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "mrope_section": [
+      8,
+      12,
+      12
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 10000.0,
+  "text_config": {
+    "architectures": [
+      "Glm4vForConditionalGeneration"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+      151329,
+      151336,
+      151338,
+      151348
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 13696,
+    "max_position_embeddings": 65536,
+    "model_type": "glm4v_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "mrope_section": [
+        8,
+        12,
+        12
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 10000.0,
+    "use_cache": true,
+    "video_token_id": null,
+    "vocab_size": 151552
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": false,
+  "video_end_token_id": 151342,
+  "video_start_token_id": 151341,
+  "video_token_id": 151344,
+  "vision_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "silu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1536,
+    "image_size": 336,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 13696,
+    "model_type": "glm4v",
+    "num_heads": 12,
+    "out_hidden_size": 4096,
+    "patch_size": 14,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151329,
+    151336,
+    151338,
+    151348
+  ],
+  "pad_token_id": 151329,
+  "temperature": 0.8,
+  "top_k": 2,
+  "top_p": 0.6,
+  "transformers_version": "4.56.1"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2150b4879e1aa0af59e7866614af67ecfec4f754d3141410e542899e4105f7
+size 4953999648

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4d094bc61da815277b2915fbe20ced0814ea99f916bc47e3c54ccec15bf488
+size 4895276872

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea03f41406350c74e6fb20bf66f959410ef477ed032d944f4f26034b398c384
+size 4895276936

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb27efea5064cfcc323483c403b9704f2128ce767331cbdeacf2d0b3e6a25dc
+size 4599576544

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2c7a244cf62c47799d634955d453af50e7bcc7b6766e818f756d29365d9150
+size 1241514112

model.safetensors.index.json

@@ -0,0 +1,712 @@
+{
+  "metadata": {
+    "total_parameters": 10292777472,
+    "total_size": 20585554944
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00005.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.downsample.bias": "model-00001-of-00005.safetensors",
+    "model.visual.downsample.weight": "model-00001-of-00005.safetensors",
+    "model.visual.embeddings.position_embedding.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.post_projection_norm.bias": "model-00001-of-00005.safetensors",
+    "model.visual.merger.post_projection_norm.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00005.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.post_conv_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.visual.post_layernorm.weight": "model-00001-of-00005.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,35 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Glm4vImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "merge_size": 2,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 9633792,
+    "shortest_edge": 12544
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|image|>",
+    "<|video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d802c61882d225c2038222543d647b34120c74486437c98031edfdf7611e1c5f
+size 19968350

tokenizer_config.json

@@ -0,0 +1,221 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151345": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151346": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151347": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151348": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151349": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151350": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|image|>",
+    "<|video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 65536,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "Glm4vProcessor",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792a217480e944ea27369d31a75ce8f61be932dc83e5cf7924d90b72783998b1
+size 6289

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_image_size": {
+    "longest_edge": 47040000
+  },
+  "merge_size": 2,
+  "num_frames": 16,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 47040000,
+    "shortest_edge": 12544
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Glm4vVideoProcessor"
+}