Upload folder using huggingface_hub

.gitattributes

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

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 +1,71 @@
+{
+  "architectures": [
+    "Glm4vForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_end_token_id": 151340,
+  "image_start_token_id": 151339,
+  "image_token_id": 151343,
+  "model_type": "glm4v",
+  "text_config": {
+    "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"
+    },
+    "rope_theta": 10000,
+    "use_cache": true,
+    "video_token_id": null,
+    "vocab_size": 151552
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "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
+  }
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338,
+    151348
+  ],
+  "pad_token_id": 151329,
+  "temperature": 0.8,
+  "top_k": 2,
+  "top_p": 0.6,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed982ba77f6581387a7c4cd710f031a73304133727e94df7f85b3b6fa54bf38a
+size 4953999648

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accbc78fdc5fb34677d1556d3dc7400e7778dcd1b53f6e81b19266aeda8befb6
+size 4895276872

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa4bd92047c9a4192e33aee43dd6ef686b3c0df6d1312b2630f40f03498cf07
+size 4895276936

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db0977c9e408b87d180174a37d8d5e517d135c1787fcd0939c77b0fdf60cbd8
+size 4599576544

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5612395cbf294074826790a9affffc5ba2e3a694a3745566a55d62be2b3fb0
+size 1241514112

model.safetensors.index.json

@@ -0,0 +1,712 @@
+{
+  "metadata": {
+    "total_parameters": 934400,
+    "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 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Glm4vImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "merge_size": 2,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "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 sha256:6c61622efca9945e2a579a0d10e7a2171800351e86e42974583268c8d38525df
+size 19968182

tokenizer_config.json

@@ -0,0 +1,220 @@
+{
+  "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": true
+    },
+    "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"
+}

trainer_state.json

@@ -0,0 +1,951 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007616146230007616,
+      "grad_norm": 11.835048123794566,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 1.116,
+      "step": 10
+    },
+    {
+      "epoch": 0.015232292460015232,
+      "grad_norm": 7.842644391089767,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.6669,
+      "step": 20
+    },
+    {
+      "epoch": 0.02284843869002285,
+      "grad_norm": 6.595317969410114,
+      "learning_rate": 2.9e-06,
+      "loss": 0.4144,
+      "step": 30
+    },
+    {
+      "epoch": 0.030464584920030464,
+      "grad_norm": 16.197313330329298,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.3473,
+      "step": 40
+    },
+    {
+      "epoch": 0.03808073115003808,
+      "grad_norm": 4.777059040290485,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.362,
+      "step": 50
+    },
+    {
+      "epoch": 0.0456968773800457,
+      "grad_norm": 3.612615550268976,
+      "learning_rate": 4.96437054631829e-06,
+      "loss": 0.34,
+      "step": 60
+    },
+    {
+      "epoch": 0.053313023610053314,
+      "grad_norm": 7.269116816605792,
+      "learning_rate": 4.9247822644497236e-06,
+      "loss": 0.3249,
+      "step": 70
+    },
+    {
+      "epoch": 0.06092916984006093,
+      "grad_norm": 3.0945431020260736,
+      "learning_rate": 4.885193982581156e-06,
+      "loss": 0.3253,
+      "step": 80
+    },
+    {
+      "epoch": 0.06854531607006854,
+      "grad_norm": 3.887936623809588,
+      "learning_rate": 4.84560570071259e-06,
+      "loss": 0.334,
+      "step": 90
+    },
+    {
+      "epoch": 0.07616146230007616,
+      "grad_norm": 5.646977694480739,
+      "learning_rate": 4.806017418844022e-06,
+      "loss": 0.3363,
+      "step": 100
+    },
+    {
+      "epoch": 0.08377760853008377,
+      "grad_norm": 4.652949981700683,
+      "learning_rate": 4.7664291369754555e-06,
+      "loss": 0.3497,
+      "step": 110
+    },
+    {
+      "epoch": 0.0913937547600914,
+      "grad_norm": 4.016803732481575,
+      "learning_rate": 4.726840855106889e-06,
+      "loss": 0.3003,
+      "step": 120
+    },
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 2.8480975606159906,
+      "learning_rate": 4.687252573238322e-06,
+      "loss": 0.2753,
+      "step": 130
+    },
+    {
+      "epoch": 0.10662604722010663,
+      "grad_norm": 5.306261875252713,
+      "learning_rate": 4.647664291369755e-06,
+      "loss": 0.3504,
+      "step": 140
+    },
+    {
+      "epoch": 0.11424219345011424,
+      "grad_norm": 3.9644170984253515,
+      "learning_rate": 4.608076009501188e-06,
+      "loss": 0.2829,
+      "step": 150
+    },
+    {
+      "epoch": 0.12185833968012186,
+      "grad_norm": 7.0071669557603045,
+      "learning_rate": 4.568487727632621e-06,
+      "loss": 0.3065,
+      "step": 160
+    },
+    {
+      "epoch": 0.12947448591012947,
+      "grad_norm": 7.924765186334578,
+      "learning_rate": 4.528899445764054e-06,
+      "loss": 0.2927,
+      "step": 170
+    },
+    {
+      "epoch": 0.1370906321401371,
+      "grad_norm": 2.679434562992301,
+      "learning_rate": 4.489311163895487e-06,
+      "loss": 0.2996,
+      "step": 180
+    },
+    {
+      "epoch": 0.1447067783701447,
+      "grad_norm": 2.894427683403079,
+      "learning_rate": 4.449722882026921e-06,
+      "loss": 0.3136,
+      "step": 190
+    },
+    {
+      "epoch": 0.15232292460015232,
+      "grad_norm": 5.923531882150988,
+      "learning_rate": 4.410134600158353e-06,
+      "loss": 0.2734,
+      "step": 200
+    },
+    {
+      "epoch": 0.15993907083015993,
+      "grad_norm": 4.285103721371967,
+      "learning_rate": 4.3705463182897865e-06,
+      "loss": 0.2679,
+      "step": 210
+    },
+    {
+      "epoch": 0.16755521706016754,
+      "grad_norm": 6.673762676336573,
+      "learning_rate": 4.33095803642122e-06,
+      "loss": 0.2628,
+      "step": 220
+    },
+    {
+      "epoch": 0.17517136329017516,
+      "grad_norm": 4.871044331385097,
+      "learning_rate": 4.291369754552653e-06,
+      "loss": 0.2776,
+      "step": 230
+    },
+    {
+      "epoch": 0.1827875095201828,
+      "grad_norm": 5.091838723173423,
+      "learning_rate": 4.251781472684085e-06,
+      "loss": 0.2539,
+      "step": 240
+    },
+    {
+      "epoch": 0.19040365575019041,
+      "grad_norm": 3.4527086586576083,
+      "learning_rate": 4.212193190815519e-06,
+      "loss": 0.2445,
+      "step": 250
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 3.695127168590451,
+      "learning_rate": 4.1726049089469524e-06,
+      "loss": 0.2917,
+      "step": 260
+    },
+    {
+      "epoch": 0.20563594821020564,
+      "grad_norm": 4.411690290365369,
+      "learning_rate": 4.133016627078385e-06,
+      "loss": 0.2507,
+      "step": 270
+    },
+    {
+      "epoch": 0.21325209444021326,
+      "grad_norm": 2.91470425056368,
+      "learning_rate": 4.093428345209818e-06,
+      "loss": 0.2586,
+      "step": 280
+    },
+    {
+      "epoch": 0.22086824067022087,
+      "grad_norm": 4.6941501972309645,
+      "learning_rate": 4.053840063341251e-06,
+      "loss": 0.2732,
+      "step": 290
+    },
+    {
+      "epoch": 0.2284843869002285,
+      "grad_norm": 3.65469328683858,
+      "learning_rate": 4.014251781472684e-06,
+      "loss": 0.2592,
+      "step": 300
+    },
+    {
+      "epoch": 0.2361005331302361,
+      "grad_norm": 7.340914536012835,
+      "learning_rate": 3.9746634996041175e-06,
+      "loss": 0.2762,
+      "step": 310
+    },
+    {
+      "epoch": 0.24371667936024372,
+      "grad_norm": 4.978603041007075,
+      "learning_rate": 3.935075217735551e-06,
+      "loss": 0.2595,
+      "step": 320
+    },
+    {
+      "epoch": 0.25133282559025133,
+      "grad_norm": 4.3081870746388224,
+      "learning_rate": 3.895486935866984e-06,
+      "loss": 0.2353,
+      "step": 330
+    },
+    {
+      "epoch": 0.25894897182025894,
+      "grad_norm": 4.039525885685747,
+      "learning_rate": 3.855898653998416e-06,
+      "loss": 0.2612,
+      "step": 340
+    },
+    {
+      "epoch": 0.26656511805026656,
+      "grad_norm": 7.773254136654106,
+      "learning_rate": 3.81631037212985e-06,
+      "loss": 0.2461,
+      "step": 350
+    },
+    {
+      "epoch": 0.2741812642802742,
+      "grad_norm": 5.337707227198452,
+      "learning_rate": 3.7767220902612826e-06,
+      "loss": 0.2558,
+      "step": 360
+    },
+    {
+      "epoch": 0.2817974105102818,
+      "grad_norm": 6.423197178565075,
+      "learning_rate": 3.7371338083927162e-06,
+      "loss": 0.2292,
+      "step": 370
+    },
+    {
+      "epoch": 0.2894135567402894,
+      "grad_norm": 18.774710142232706,
+      "learning_rate": 3.697545526524149e-06,
+      "loss": 0.2453,
+      "step": 380
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 7.135948853519646,
+      "learning_rate": 3.657957244655582e-06,
+      "loss": 0.2304,
+      "step": 390
+    },
+    {
+      "epoch": 0.30464584920030463,
+      "grad_norm": 16.602438244874765,
+      "learning_rate": 3.6183689627870154e-06,
+      "loss": 0.2837,
+      "step": 400
+    },
+    {
+      "epoch": 0.31226199543031224,
+      "grad_norm": 7.063664027325613,
+      "learning_rate": 3.578780680918448e-06,
+      "loss": 0.2686,
+      "step": 410
+    },
+    {
+      "epoch": 0.31987814166031986,
+      "grad_norm": 9.41480626347556,
+      "learning_rate": 3.5391923990498818e-06,
+      "loss": 0.2857,
+      "step": 420
+    },
+    {
+      "epoch": 0.3274942878903275,
+      "grad_norm": 6.31014103739446,
+      "learning_rate": 3.4996041171813145e-06,
+      "loss": 0.2812,
+      "step": 430
+    },
+    {
+      "epoch": 0.3351104341203351,
+      "grad_norm": 5.189791913301834,
+      "learning_rate": 3.4600158353127477e-06,
+      "loss": 0.2567,
+      "step": 440
+    },
+    {
+      "epoch": 0.3427265803503427,
+      "grad_norm": 9.568482976958887,
+      "learning_rate": 3.4204275534441805e-06,
+      "loss": 0.2641,
+      "step": 450
+    },
+    {
+      "epoch": 0.3503427265803503,
+      "grad_norm": 3.364826563025041,
+      "learning_rate": 3.3808392715756137e-06,
+      "loss": 0.2545,
+      "step": 460
+    },
+    {
+      "epoch": 0.357958872810358,
+      "grad_norm": 7.009480899792399,
+      "learning_rate": 3.3412509897070473e-06,
+      "loss": 0.2653,
+      "step": 470
+    },
+    {
+      "epoch": 0.3655750190403656,
+      "grad_norm": 5.524309651862536,
+      "learning_rate": 3.30166270783848e-06,
+      "loss": 0.2514,
+      "step": 480
+    },
+    {
+      "epoch": 0.3731911652703732,
+      "grad_norm": 3.7876676441463046,
+      "learning_rate": 3.2620744259699132e-06,
+      "loss": 0.2435,
+      "step": 490
+    },
+    {
+      "epoch": 0.38080731150038083,
+      "grad_norm": 6.168551543835485,
+      "learning_rate": 3.222486144101346e-06,
+      "loss": 0.2689,
+      "step": 500
+    },
+    {
+      "epoch": 0.38842345773038844,
+      "grad_norm": 5.50094150163915,
+      "learning_rate": 3.1828978622327796e-06,
+      "loss": 0.2454,
+      "step": 510
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 7.801936281585015,
+      "learning_rate": 3.1433095803642124e-06,
+      "loss": 0.2699,
+      "step": 520
+    },
+    {
+      "epoch": 0.4036557501904037,
+      "grad_norm": 4.436892195809717,
+      "learning_rate": 3.1037212984956456e-06,
+      "loss": 0.2536,
+      "step": 530
+    },
+    {
+      "epoch": 0.4112718964204113,
+      "grad_norm": 18.395533582841257,
+      "learning_rate": 3.0641330166270788e-06,
+      "loss": 0.2789,
+      "step": 540
+    },
+    {
+      "epoch": 0.4188880426504189,
+      "grad_norm": 4.58974339162325,
+      "learning_rate": 3.0245447347585115e-06,
+      "loss": 0.2404,
+      "step": 550
+    },
+    {
+      "epoch": 0.4265041888804265,
+      "grad_norm": 3.07844758325921,
+      "learning_rate": 2.984956452889945e-06,
+      "loss": 0.2544,
+      "step": 560
+    },
+    {
+      "epoch": 0.43412033511043413,
+      "grad_norm": 11.355633136686789,
+      "learning_rate": 2.945368171021378e-06,
+      "loss": 0.251,
+      "step": 570
+    },
+    {
+      "epoch": 0.44173648134044174,
+      "grad_norm": 6.877211875578664,
+      "learning_rate": 2.905779889152811e-06,
+      "loss": 0.2546,
+      "step": 580
+    },
+    {
+      "epoch": 0.44935262757044936,
+      "grad_norm": 2.1130575081798493,
+      "learning_rate": 2.866191607284244e-06,
+      "loss": 0.2458,
+      "step": 590
+    },
+    {
+      "epoch": 0.456968773800457,
+      "grad_norm": 6.059827920107357,
+      "learning_rate": 2.826603325415677e-06,
+      "loss": 0.2313,
+      "step": 600
+    },
+    {
+      "epoch": 0.4645849200304646,
+      "grad_norm": 4.797362022426609,
+      "learning_rate": 2.7870150435471106e-06,
+      "loss": 0.2329,
+      "step": 610
+    },
+    {
+      "epoch": 0.4722010662604722,
+      "grad_norm": 2.9020896003162875,
+      "learning_rate": 2.7474267616785434e-06,
+      "loss": 0.258,
+      "step": 620
+    },
+    {
+      "epoch": 0.4798172124904798,
+      "grad_norm": 3.5954255971397653,
+      "learning_rate": 2.7078384798099766e-06,
+      "loss": 0.2344,
+      "step": 630
+    },
+    {
+      "epoch": 0.48743335872048743,
+      "grad_norm": 4.973309240009862,
+      "learning_rate": 2.6682501979414094e-06,
+      "loss": 0.2647,
+      "step": 640
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 4.202207460409975,
+      "learning_rate": 2.6286619160728426e-06,
+      "loss": 0.2213,
+      "step": 650
+    },
+    {
+      "epoch": 0.5026656511805027,
+      "grad_norm": 2.7235992530661695,
+      "learning_rate": 2.5890736342042753e-06,
+      "loss": 0.2086,
+      "step": 660
+    },
+    {
+      "epoch": 0.5102817974105103,
+      "grad_norm": 8.31402385598321,
+      "learning_rate": 2.549485352335709e-06,
+      "loss": 0.2214,
+      "step": 670
+    },
+    {
+      "epoch": 0.5178979436405179,
+      "grad_norm": 5.150239251986413,
+      "learning_rate": 2.509897070467142e-06,
+      "loss": 0.2248,
+      "step": 680
+    },
+    {
+      "epoch": 0.5255140898705255,
+      "grad_norm": 2.063111564649914,
+      "learning_rate": 2.470308788598575e-06,
+      "loss": 0.2176,
+      "step": 690
+    },
+    {
+      "epoch": 0.5331302361005331,
+      "grad_norm": 2.6602413962762723,
+      "learning_rate": 2.430720506730008e-06,
+      "loss": 0.2078,
+      "step": 700
+    },
+    {
+      "epoch": 0.5407463823305407,
+      "grad_norm": 4.256322056465414,
+      "learning_rate": 2.3911322248614413e-06,
+      "loss": 0.2523,
+      "step": 710
+    },
+    {
+      "epoch": 0.5483625285605483,
+      "grad_norm": 5.612404213167897,
+      "learning_rate": 2.3515439429928744e-06,
+      "loss": 0.1892,
+      "step": 720
+    },
+    {
+      "epoch": 0.555978674790556,
+      "grad_norm": 3.396066595409222,
+      "learning_rate": 2.3119556611243072e-06,
+      "loss": 0.1999,
+      "step": 730
+    },
+    {
+      "epoch": 0.5635948210205636,
+      "grad_norm": 2.2396054043457636,
+      "learning_rate": 2.2723673792557404e-06,
+      "loss": 0.1971,
+      "step": 740
+    },
+    {
+      "epoch": 0.5712109672505712,
+      "grad_norm": 2.3958999447143667,
+      "learning_rate": 2.2327790973871736e-06,
+      "loss": 0.2502,
+      "step": 750
+    },
+    {
+      "epoch": 0.5788271134805788,
+      "grad_norm": 1.977018318704205,
+      "learning_rate": 2.1931908155186068e-06,
+      "loss": 0.1889,
+      "step": 760
+    },
+    {
+      "epoch": 0.5864432597105864,
+      "grad_norm": 8.354339753870269,
+      "learning_rate": 2.1536025336500395e-06,
+      "loss": 0.2236,
+      "step": 770
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 5.047427806944594,
+      "learning_rate": 2.114014251781473e-06,
+      "loss": 0.2243,
+      "step": 780
+    },
+    {
+      "epoch": 0.6016755521706016,
+      "grad_norm": 2.4089372949840833,
+      "learning_rate": 2.074425969912906e-06,
+      "loss": 0.2004,
+      "step": 790
+    },
+    {
+      "epoch": 0.6092916984006093,
+      "grad_norm": 4.550685815329762,
+      "learning_rate": 2.034837688044339e-06,
+      "loss": 0.2139,
+      "step": 800
+    },
+    {
+      "epoch": 0.6169078446306169,
+      "grad_norm": 4.373033096667755,
+      "learning_rate": 1.9952494061757723e-06,
+      "loss": 0.2004,
+      "step": 810
+    },
+    {
+      "epoch": 0.6245239908606245,
+      "grad_norm": 2.4860668443690046,
+      "learning_rate": 1.955661124307205e-06,
+      "loss": 0.2174,
+      "step": 820
+    },
+    {
+      "epoch": 0.6321401370906321,
+      "grad_norm": 6.985461338636023,
+      "learning_rate": 1.9160728424386383e-06,
+      "loss": 0.2018,
+      "step": 830
+    },
+    {
+      "epoch": 0.6397562833206397,
+      "grad_norm": 2.494187139035971,
+      "learning_rate": 1.8764845605700712e-06,
+      "loss": 0.1817,
+      "step": 840
+    },
+    {
+      "epoch": 0.6473724295506473,
+      "grad_norm": 5.371564360686615,
+      "learning_rate": 1.8368962787015046e-06,
+      "loss": 0.2318,
+      "step": 850
+    },
+    {
+      "epoch": 0.654988575780655,
+      "grad_norm": 4.536677734185734,
+      "learning_rate": 1.7973079968329376e-06,
+      "loss": 0.2293,
+      "step": 860
+    },
+    {
+      "epoch": 0.6626047220106626,
+      "grad_norm": 3.3728431484538737,
+      "learning_rate": 1.7577197149643708e-06,
+      "loss": 0.2361,
+      "step": 870
+    },
+    {
+      "epoch": 0.6702208682406702,
+      "grad_norm": 1.6073529320120856,
+      "learning_rate": 1.7181314330958038e-06,
+      "loss": 0.1968,
+      "step": 880
+    },
+    {
+      "epoch": 0.6778370144706778,
+      "grad_norm": 2.1015646443463605,
+      "learning_rate": 1.6785431512272367e-06,
+      "loss": 0.2219,
+      "step": 890
+    },
+    {
+      "epoch": 0.6854531607006854,
+      "grad_norm": 2.318400190633724,
+      "learning_rate": 1.63895486935867e-06,
+      "loss": 0.2322,
+      "step": 900
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 3.122592092936656,
+      "learning_rate": 1.599366587490103e-06,
+      "loss": 0.241,
+      "step": 910
+    },
+    {
+      "epoch": 0.7006854531607006,
+      "grad_norm": 3.904435708637386,
+      "learning_rate": 1.5597783056215363e-06,
+      "loss": 0.2017,
+      "step": 920
+    },
+    {
+      "epoch": 0.7083015993907082,
+      "grad_norm": 2.4588794352649397,
+      "learning_rate": 1.5201900237529693e-06,
+      "loss": 0.1908,
+      "step": 930
+    },
+    {
+      "epoch": 0.715917745620716,
+      "grad_norm": 3.8014556275662774,
+      "learning_rate": 1.4806017418844023e-06,
+      "loss": 0.2018,
+      "step": 940
+    },
+    {
+      "epoch": 0.7235338918507236,
+      "grad_norm": 1.7382325918516672,
+      "learning_rate": 1.4410134600158355e-06,
+      "loss": 0.2021,
+      "step": 950
+    },
+    {
+      "epoch": 0.7311500380807312,
+      "grad_norm": 2.8111839390766216,
+      "learning_rate": 1.4014251781472684e-06,
+      "loss": 0.2169,
+      "step": 960
+    },
+    {
+      "epoch": 0.7387661843107388,
+      "grad_norm": 4.2660511964815875,
+      "learning_rate": 1.3618368962787016e-06,
+      "loss": 0.2203,
+      "step": 970
+    },
+    {
+      "epoch": 0.7463823305407464,
+      "grad_norm": 6.971263503890589,
+      "learning_rate": 1.3222486144101346e-06,
+      "loss": 0.1991,
+      "step": 980
+    },
+    {
+      "epoch": 0.753998476770754,
+      "grad_norm": 8.292979602981546,
+      "learning_rate": 1.282660332541568e-06,
+      "loss": 0.2047,
+      "step": 990
+    },
+    {
+      "epoch": 0.7616146230007617,
+      "grad_norm": 4.030895551326649,
+      "learning_rate": 1.2430720506730008e-06,
+      "loss": 0.227,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 2.562977198803812,
+      "learning_rate": 1.203483768804434e-06,
+      "loss": 0.1728,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7768469154607769,
+      "grad_norm": 2.503974634764323,
+      "learning_rate": 1.1638954869358671e-06,
+      "loss": 0.1971,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7844630616907845,
+      "grad_norm": 2.9622637791093016,
+      "learning_rate": 1.1243072050673001e-06,
+      "loss": 0.1869,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 2.0051653354077335,
+      "learning_rate": 1.0847189231987333e-06,
+      "loss": 0.2293,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7996953541507997,
+      "grad_norm": 3.184729069100192,
+      "learning_rate": 1.0451306413301663e-06,
+      "loss": 0.2063,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8073115003808073,
+      "grad_norm": 8.324801185828381,
+      "learning_rate": 1.0055423594615995e-06,
+      "loss": 0.186,
+      "step": 1060
+    },
+    {
+      "epoch": 0.814927646610815,
+      "grad_norm": 3.0052525618271293,
+      "learning_rate": 9.659540775930324e-07,
+      "loss": 0.2087,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8225437928408226,
+      "grad_norm": 22.015701113681754,
+      "learning_rate": 9.263657957244656e-07,
+      "loss": 0.2595,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8301599390708302,
+      "grad_norm": 2.4553515877726535,
+      "learning_rate": 8.867775138558987e-07,
+      "loss": 0.1702,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8377760853008378,
+      "grad_norm": 2.162378595346796,
+      "learning_rate": 8.471892319873318e-07,
+      "loss": 0.1864,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8453922315308454,
+      "grad_norm": 2.8013200458499994,
+      "learning_rate": 8.07600950118765e-07,
+      "loss": 0.2157,
+      "step": 1110
+    },
+    {
+      "epoch": 0.853008377760853,
+      "grad_norm": 3.6104191007542608,
+      "learning_rate": 7.680126682501981e-07,
+      "loss": 0.2147,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8606245239908606,
+      "grad_norm": 3.3981713373449347,
+      "learning_rate": 7.28424386381631e-07,
+      "loss": 0.2242,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8682406702208683,
+      "grad_norm": 2.5235731123816096,
+      "learning_rate": 6.888361045130641e-07,
+      "loss": 0.1686,
+      "step": 1140
+    },
+    {
+      "epoch": 0.8758568164508759,
+      "grad_norm": 17.92455537528504,
+      "learning_rate": 6.492478226444973e-07,
+      "loss": 0.1884,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8834729626808835,
+      "grad_norm": 1.8092517385846119,
+      "learning_rate": 6.096595407759304e-07,
+      "loss": 0.1654,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 6.630711115030937,
+      "learning_rate": 5.700712589073635e-07,
+      "loss": 0.1963,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8987052551408987,
+      "grad_norm": 4.752180632682597,
+      "learning_rate": 5.304829770387966e-07,
+      "loss": 0.2126,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9063214013709063,
+      "grad_norm": 3.262231573492007,
+      "learning_rate": 4.908946951702296e-07,
+      "loss": 0.1937,
+      "step": 1190
+    },
+    {
+      "epoch": 0.913937547600914,
+      "grad_norm": 2.694587750125678,
+      "learning_rate": 4.5130641330166273e-07,
+      "loss": 0.2039,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9215536938309216,
+      "grad_norm": 3.8952707228642507,
+      "learning_rate": 4.1171813143309587e-07,
+      "loss": 0.2073,
+      "step": 1210
+    },
+    {
+      "epoch": 0.9291698400609292,
+      "grad_norm": 3.6728115952215172,
+      "learning_rate": 3.721298495645289e-07,
+      "loss": 0.2099,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9367859862909368,
+      "grad_norm": 2.4955892161466164,
+      "learning_rate": 3.3254156769596203e-07,
+      "loss": 0.1877,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9444021325209444,
+      "grad_norm": 2.7829353934232635,
+      "learning_rate": 2.929532858273951e-07,
+      "loss": 0.1921,
+      "step": 1240
+    },
+    {
+      "epoch": 0.952018278750952,
+      "grad_norm": 1.8391655577692532,
+      "learning_rate": 2.533650039588282e-07,
+      "loss": 0.2154,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9596344249809596,
+      "grad_norm": 5.945610666641174,
+      "learning_rate": 2.1377672209026128e-07,
+      "loss": 0.2052,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9672505712109672,
+      "grad_norm": 3.466683424087242,
+      "learning_rate": 1.7418844022169442e-07,
+      "loss": 0.1855,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9748667174409749,
+      "grad_norm": 3.7618841125617637,
+      "learning_rate": 1.3460015835312747e-07,
+      "loss": 0.2226,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9824828636709825,
+      "grad_norm": 2.507736397987616,
+      "learning_rate": 9.501187648456058e-08,
+      "loss": 0.1852,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 2.5513116117371135,
+      "learning_rate": 5.542359461599367e-08,
+      "loss": 0.1866,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9977151561309977,
+      "grad_norm": 2.649721331069317,
+      "learning_rate": 1.5835312747426762e-08,
+      "loss": 0.187,
+      "step": 1310
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1313,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1736915245596672.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e729c0d402c2114e4b37b07473d0ab2fb0cbb91a9498bc15bc4120fb8c238770
+size 7160

video_preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "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_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,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 47040000,
+    "shortest_edge": 12544
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Glm4vVideoProcessor"
+}