初始化项目，由ModelHub XC社区提供模型
Model: luca0621/appgen-qwen25-uedgrpo-completion-bootstrap-v25-best-heldout Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
31
appgen_grpo_manifest.json
Normal file
31
appgen_grpo_manifest.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"created_at_utc": "2026-07-16T23:31:52.277671+00:00",
|
||||
"global_step": 95,
|
||||
"load_validation": {
|
||||
"parameter_count": 8292166656,
|
||||
"processor_probe_fields": 4,
|
||||
"processor_probe_tensor_values": 28311,
|
||||
"sampled_tensors": 32,
|
||||
"tokenizer_contract_files": 7
|
||||
},
|
||||
"model_config": {
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"hidden_size": 3584,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"vision_hidden_size": 1280,
|
||||
"vision_model_type": "qwen2_5_vl",
|
||||
"vocab_size": 152064
|
||||
},
|
||||
"run_manifest_sha256": null,
|
||||
"run_name": "uedgpo_q25_unified_completion_bootstrap_8g_v25_step0",
|
||||
"schema_version": 1,
|
||||
"source": "global_step_95/actor",
|
||||
"system_prompt": {
|
||||
"bytes": 2403,
|
||||
"filename": "appgen_system_prompt.txt",
|
||||
"sha256": "22f4ad304b625269de3530faff544d6a9cfc75ec800eafc625cf9761e6799cf5"
|
||||
},
|
||||
"training_contract": {}
|
||||
}
|
||||
28
appgen_system_prompt.txt
Normal file
28
appgen_system_prompt.txt
Normal file
@@ -0,0 +1,28 @@
|
||||
You are a helpful assistant.
|
||||
|
||||
|
||||
# Tools
|
||||
|
||||
You may call one or more functions to assist with the user query.
|
||||
|
||||
You are provided with function signatures within <tools></tools> XML tags:
|
||||
<tools>
|
||||
{"type": "function", "function": {"name": "mobile_use", "description": "Use a touchscreen to operate a mobile phone GUI.
|
||||
* This is an interface to a mobile device with a touchscreen. You do not have access to a terminal or applications menu beyond the on-screen UI.
|
||||
* All coordinates are ABSOLUTE pixel positions of the on-screen element, where (0,0) is the top-left corner of the screen.
|
||||
* Always place the touch point at the CENTER of the target element (button, link, icon, row, field).", "parameters": {"properties": {"action": {"description": "The action to perform. The available actions are:
|
||||
* `click`: Tap the screen at `coordinate`.
|
||||
* `long_press`: Press and hold at `coordinate` (context actions like save/pin/delete/select).
|
||||
* `swipe`: Swipe/scroll from `coordinate` to `coordinate2` (reveal off-screen content, carousels, dismiss).
|
||||
* `type`: Type `text` into the currently focused input field.
|
||||
* `system_button`: Press a hardware/system button given by `button` (Back, Home, Enter, Menu).
|
||||
* `open_app`: Open the app named `text` from the launcher/home screen.
|
||||
* `wait`: Wait briefly for the screen to update.
|
||||
* `terminate`: End the task; `status` is `success` or `failure`.
|
||||
* `answer`: Reply to the user with `text` (for question-answering tasks).", "enum": ["click", "long_press", "swipe", "type", "system_button", "open_app", "wait", "terminate", "answer"], "type": "string"}, "coordinate": {"description": "(x, y): absolute pixel target point for `click` / `long_press`, and the START point for `swipe`.", "type": "array"}, "coordinate2": {"description": "(x, y): absolute pixel END point for `swipe`.", "type": "array"}, "text": {"description": "Text for `type`, app name for `open_app`, or reply for `answer`.", "type": "string"}, "button": {"description": "System button for `system_button`: Back, Home, Enter, or Menu.", "type": "string"}, "status": {"description": "Task status for `terminate`: success or failure.", "type": "string"}}, "required": ["action"], "type": "object"}}}
|
||||
</tools>
|
||||
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{"name": <function-name>, "arguments": <args-json-object>}
|
||||
</tool_call>
|
||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
||||
You are a helpful assistant.<|im_end|>
|
||||
{% endif %}<|im_start|>{{ message['role'] }}
|
||||
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
||||
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
||||
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
||||
{% endif %}
|
||||
133
config.json
Normal file
133
config.json
Normal file
@@ -0,0 +1,133 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"text_config": {
|
||||
"_name_or_path": "/data/appgen/verl_q25_completion_bootstrap_resume_s20_s100_v26_ckpts/global_step_95/actor",
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl_text",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.3",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"dtype": "float32",
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3420,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_heads": 16,
|
||||
"out_hidden_size": 3584,
|
||||
"pad_token_id": 151643,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"tokens_per_second": 2,
|
||||
"window_size": 112
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 1e-06,
|
||||
"transformers_version": "4.57.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34447d63c39ed485bdd48b2794f0345de052bae2129a2bc4dc6d9cb0c9132fdd
|
||||
size 4960688760
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c0b89a0a3928d872ef41685630104d05f238ae94f151a869dca568a4e27d4bf9
|
||||
size 4974346560
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:429556bfefee2db5b28a4daf682010eb8d465791849b847d5770c4dd758acb4c
|
||||
size 4897395808
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f434d8ccc4f36b2fed3d98ae1cdd8dd886813af269396d0b350d1066c66e4ab1
|
||||
size 1751983336
|
||||
737
model.safetensors.index.json
Normal file
737
model.safetensors.index.json
Normal file
@@ -0,0 +1,737 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8292166656,
|
||||
"total_size": 16584333312
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00002-of-00004.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00002-of-00004.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00002-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
39
preprocessor_config.json
Normal file
39
preprocessor_config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"pad_size": null,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
43
video_preprocessor_config.json
Normal file
43
video_preprocessor_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": false,
|
||||
"fps": null,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_frames": 768,
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"min_pixels": 3136,
|
||||
"num_frames": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "Qwen2VLVideoProcessor"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user