Upload folder using huggingface_hub
Browse files- .gitattributes +26 -10
- added_tokens.json +24 -0
- assets/examples/car.png +3 -0
- assets/illustrations/architecture.png +3 -0
- assets/illustrations/cover.jpg +3 -0
- assets/illustrations/gen_edit.jpg +3 -0
- chat_template.json +3 -0
- config.json +56 -0
- configuration.json +1 -0
- configuration_qwen2_5_vl.py +258 -0
- decoder_81_512.bin +3 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +737 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,51 @@
|
|
| 1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 4 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
| 5 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 11 |
*.model filter=lfs diff=lfs merge=lfs -text
|
| 12 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
| 13 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 14 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 15 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 16 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
| 17 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 18 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 19 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 20 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 21 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 22 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 23 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 24 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.db* filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.ark* filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.ggml filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 46 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -textassets/examples/car.png filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
assets/illustrations/architecture.png filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
assets/illustrations/cover.jpg filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
assets/illustrations/gen_edit.jpg filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
assets/examples/car.png
ADDED
|
Git LFS Details
|
assets/illustrations/architecture.png
ADDED
|
Git LFS Details
|
assets/illustrations/cover.jpg
ADDED
|
Git LFS Details
|
assets/illustrations/gen_edit.jpg
ADDED
|
Git LFS Details
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "DiffSynth-Studio/Nexus-Gen",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_qwen2_5_vl.Qwen2_5_VLConfig",
|
| 9 |
+
"AutoModel": "modeling_qwen2_5_vl.Qwen2_5_VLModel",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_qwen2_5_vl.Qwen2_5_VLForConditionalGeneration"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 151643,
|
| 13 |
+
"eos_token_id": 151645,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 3584,
|
| 16 |
+
"image_token_id": 151655,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 18944,
|
| 19 |
+
"max_position_embeddings": 128000,
|
| 20 |
+
"max_window_layers": 28,
|
| 21 |
+
"model_type": "qwen2_5_vl",
|
| 22 |
+
"num_attention_heads": 28,
|
| 23 |
+
"num_hidden_layers": 28,
|
| 24 |
+
"num_key_value_heads": 4,
|
| 25 |
+
"pad_token_id": 151643,
|
| 26 |
+
"rms_norm_eps": 1e-06,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"mrope_section": [
|
| 29 |
+
16,
|
| 30 |
+
24,
|
| 31 |
+
24
|
| 32 |
+
],
|
| 33 |
+
"rope_type": "default",
|
| 34 |
+
"type": "default"
|
| 35 |
+
},
|
| 36 |
+
"rope_theta": 1000000.0,
|
| 37 |
+
"sliding_window": 32768,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"torch_dtype": "bfloat16",
|
| 40 |
+
"transformers_version": "4.49.0",
|
| 41 |
+
"use_cache": false,
|
| 42 |
+
"use_sliding_window": false,
|
| 43 |
+
"video_token_id": 151656,
|
| 44 |
+
"vision_config": {
|
| 45 |
+
"hidden_size": 1280,
|
| 46 |
+
"in_chans": 3,
|
| 47 |
+
"model_type": "qwen2_5_vl",
|
| 48 |
+
"spatial_patch_size": 14,
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"torch_dtype": "bfloat16"
|
| 51 |
+
},
|
| 52 |
+
"vision_end_token_id": 151653,
|
| 53 |
+
"vision_start_token_id": 151652,
|
| 54 |
+
"vision_token_id": 151654,
|
| 55 |
+
"vocab_size": 152064
|
| 56 |
+
}
|
configuration.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"framework":"Pytorch","task":"any-to-any"}
|
configuration_qwen2_5_vl.py
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
| 2 |
+
# This file was automatically generated from src/transformers/models/qwen2_5_vl/modular_qwen2_5_vl.py.
|
| 3 |
+
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
| 4 |
+
# the file from the modular. If any change should be done, please apply the change to the
|
| 5 |
+
# modular_qwen2_5_vl.py file directly. One of our CI enforces this.
|
| 6 |
+
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
| 7 |
+
# coding=utf-8
|
| 8 |
+
# Copyright 2025 The Qwen Team and The HuggingFace Inc. team. All rights reserved.
|
| 9 |
+
#
|
| 10 |
+
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
|
| 11 |
+
# and OPT implementations in this library. It has been modified from its
|
| 12 |
+
# original forms to accommodate minor architectural differences compared
|
| 13 |
+
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
|
| 14 |
+
#
|
| 15 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 16 |
+
# you may not use this file except in compliance with the License.
|
| 17 |
+
# You may obtain a copy of the License at
|
| 18 |
+
#
|
| 19 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 20 |
+
#
|
| 21 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 22 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 23 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 24 |
+
# See the License for the specific language governing permissions and
|
| 25 |
+
# limitations under the License.
|
| 26 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 27 |
+
from transformers.modeling_rope_utils import rope_config_validation
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
class Qwen2_5_VLVisionConfig(PretrainedConfig):
|
| 31 |
+
model_type = "qwen2_5_vl"
|
| 32 |
+
base_config_key = "vision_config"
|
| 33 |
+
|
| 34 |
+
def __init__(
|
| 35 |
+
self,
|
| 36 |
+
depth=32,
|
| 37 |
+
hidden_size=3584,
|
| 38 |
+
hidden_act="silu",
|
| 39 |
+
intermediate_size=3420,
|
| 40 |
+
num_heads=16,
|
| 41 |
+
in_channels=3,
|
| 42 |
+
patch_size=14,
|
| 43 |
+
spatial_merge_size=2,
|
| 44 |
+
temporal_patch_size=2,
|
| 45 |
+
tokens_per_second=4,
|
| 46 |
+
window_size=112,
|
| 47 |
+
out_hidden_size=3584,
|
| 48 |
+
fullatt_block_indexes=[7, 15, 23, 31],
|
| 49 |
+
**kwargs,
|
| 50 |
+
):
|
| 51 |
+
super().__init__(**kwargs)
|
| 52 |
+
|
| 53 |
+
self.depth = depth
|
| 54 |
+
self.hidden_size = hidden_size
|
| 55 |
+
self.hidden_act = hidden_act
|
| 56 |
+
self.intermediate_size = intermediate_size
|
| 57 |
+
self.num_heads = num_heads
|
| 58 |
+
self.in_channels = in_channels
|
| 59 |
+
self.patch_size = patch_size
|
| 60 |
+
self.spatial_merge_size = spatial_merge_size
|
| 61 |
+
self.temporal_patch_size = temporal_patch_size
|
| 62 |
+
self.tokens_per_second = tokens_per_second
|
| 63 |
+
self.window_size = window_size
|
| 64 |
+
self.fullatt_block_indexes = fullatt_block_indexes
|
| 65 |
+
self.out_hidden_size = out_hidden_size
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
class Qwen2_5_VLConfig(PretrainedConfig):
|
| 69 |
+
r"""
|
| 70 |
+
This is the configuration class to store the configuration of a [`Qwen2_5_VLModel`]. It is used to instantiate a
|
| 71 |
+
Qwen2-VL model according to the specified arguments, defining the model architecture. Instantiating a configuration
|
| 72 |
+
with the defaults will yield a similar configuration to that of
|
| 73 |
+
Qwen2-VL-7B-Instruct [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct).
|
| 74 |
+
|
| 75 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
| 76 |
+
documentation from [`PretrainedConfig`] for more information.
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
Args:
|
| 80 |
+
vocab_size (`int`, *optional*, defaults to 152064):
|
| 81 |
+
Vocabulary size of the Qwen2_5_VL model. Defines the number of different tokens that can be represented by the
|
| 82 |
+
`inputs_ids` passed when calling [`Qwen2_5_VLModel`]
|
| 83 |
+
hidden_size (`int`, *optional*, defaults to 8192):
|
| 84 |
+
Dimension of the hidden representations.
|
| 85 |
+
intermediate_size (`int`, *optional*, defaults to 29568):
|
| 86 |
+
Dimension of the MLP representations.
|
| 87 |
+
num_hidden_layers (`int`, *optional*, defaults to 80):
|
| 88 |
+
Number of hidden layers in the Transformer encoder.
|
| 89 |
+
num_attention_heads (`int`, *optional*, defaults to 64):
|
| 90 |
+
Number of attention heads for each attention layer in the Transformer encoder.
|
| 91 |
+
num_key_value_heads (`int`, *optional*, defaults to 8):
|
| 92 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
| 93 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
| 94 |
+
`num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
| 95 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
| 96 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
| 97 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
|
| 98 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
| 99 |
+
The non-linear activation function (function or string) in the decoder.
|
| 100 |
+
max_position_embeddings (`int`, *optional*, defaults to 32768):
|
| 101 |
+
The maximum sequence length that this model might ever be used with.
|
| 102 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
| 103 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
| 104 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
| 105 |
+
The epsilon used by the rms normalization layers.
|
| 106 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
| 107 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
| 108 |
+
relevant if `config.is_decoder=True`.
|
| 109 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
| 110 |
+
Whether the model's input and output word embeddings should be tied.
|
| 111 |
+
rope_theta (`float`, *optional*, defaults to 1000000.0):
|
| 112 |
+
The base period of the RoPE embeddings.
|
| 113 |
+
use_sliding_window (`bool`, *optional*, defaults to `False`):
|
| 114 |
+
Whether to use sliding window attention.
|
| 115 |
+
sliding_window (`int`, *optional*, defaults to 4096):
|
| 116 |
+
Sliding window attention (SWA) window size. If not specified, will default to `4096`.
|
| 117 |
+
max_window_layers (`int`, *optional*, defaults to 80):
|
| 118 |
+
The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
|
| 119 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
| 120 |
+
The dropout ratio for the attention probabilities.
|
| 121 |
+
vision_config (`Dict`, *optional*):
|
| 122 |
+
The config for the visual encoder initialization.
|
| 123 |
+
rope_scaling (`Dict`, *optional*):
|
| 124 |
+
Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
|
| 125 |
+
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
|
| 126 |
+
accordingly.
|
| 127 |
+
Expected contents:
|
| 128 |
+
`rope_type` (`str`):
|
| 129 |
+
The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
|
| 130 |
+
'llama3'], with 'default' being the original RoPE implementation.
|
| 131 |
+
`factor` (`float`, *optional*):
|
| 132 |
+
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
|
| 133 |
+
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
|
| 134 |
+
original maximum pre-trained length.
|
| 135 |
+
`original_max_position_embeddings` (`int`, *optional*):
|
| 136 |
+
Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
|
| 137 |
+
pretraining.
|
| 138 |
+
`attention_factor` (`float`, *optional*):
|
| 139 |
+
Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
|
| 140 |
+
computation. If unspecified, it defaults to value recommended by the implementation, using the
|
| 141 |
+
`factor` field to infer the suggested value.
|
| 142 |
+
`beta_fast` (`float`, *optional*):
|
| 143 |
+
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
|
| 144 |
+
ramp function. If unspecified, it defaults to 32.
|
| 145 |
+
`beta_slow` (`float`, *optional*):
|
| 146 |
+
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
|
| 147 |
+
ramp function. If unspecified, it defaults to 1.
|
| 148 |
+
`short_factor` (`List[float]`, *optional*):
|
| 149 |
+
Only used with 'longrope'. The scaling factor to be applied to short contexts (<
|
| 150 |
+
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
|
| 151 |
+
size divided by the number of attention heads divided by 2
|
| 152 |
+
`long_factor` (`List[float]`, *optional*):
|
| 153 |
+
Only used with 'longrope'. The scaling factor to be applied to long contexts (<
|
| 154 |
+
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
|
| 155 |
+
size divided by the number of attention heads divided by 2
|
| 156 |
+
`low_freq_factor` (`float`, *optional*):
|
| 157 |
+
Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
|
| 158 |
+
`high_freq_factor` (`float`, *optional*):
|
| 159 |
+
Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
|
| 160 |
+
|
| 161 |
+
```python
|
| 162 |
+
>>> from transformers import Qwen2_5_VLForConditionalGeneration, Qwen2_5_VLConfig
|
| 163 |
+
|
| 164 |
+
>>> # Initializing a Qwen2_5_VL style configuration
|
| 165 |
+
>>> configuration = Qwen2_5_VLConfig()
|
| 166 |
+
|
| 167 |
+
>>> # Initializing a model from the Qwen2-VL-7B style configuration
|
| 168 |
+
>>> model = Qwen2_5_VLForConditionalGeneration(configuration)
|
| 169 |
+
|
| 170 |
+
>>> # Accessing the model configuration
|
| 171 |
+
>>> configuration = model.config
|
| 172 |
+
```"""
|
| 173 |
+
|
| 174 |
+
model_type = "qwen2_5_vl"
|
| 175 |
+
sub_configs = {"vision_config": Qwen2_5_VLVisionConfig}
|
| 176 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 177 |
+
# Default tensor parallel plan for base model `Qwen2_5_VL`
|
| 178 |
+
base_model_tp_plan = {
|
| 179 |
+
"layers.*.self_attn.q_proj": "colwise",
|
| 180 |
+
"layers.*.self_attn.k_proj": "colwise",
|
| 181 |
+
"layers.*.self_attn.v_proj": "colwise",
|
| 182 |
+
"layers.*.self_attn.o_proj": "rowwise",
|
| 183 |
+
"layers.*.mlp.gate_proj": "colwise",
|
| 184 |
+
"layers.*.mlp.up_proj": "colwise",
|
| 185 |
+
"layers.*.mlp.down_proj": "rowwise",
|
| 186 |
+
}
|
| 187 |
+
base_model_pp_plan = {
|
| 188 |
+
"embed_tokens": (["input_ids"], ["inputs_embeds"]),
|
| 189 |
+
"layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
|
| 190 |
+
"norm": (["hidden_states"], ["hidden_states"]),
|
| 191 |
+
}
|
| 192 |
+
|
| 193 |
+
def __init__(
|
| 194 |
+
self,
|
| 195 |
+
vocab_size=152064,
|
| 196 |
+
hidden_size=8192,
|
| 197 |
+
intermediate_size=29568,
|
| 198 |
+
num_hidden_layers=80,
|
| 199 |
+
num_attention_heads=64,
|
| 200 |
+
num_key_value_heads=8,
|
| 201 |
+
hidden_act="silu",
|
| 202 |
+
max_position_embeddings=32768,
|
| 203 |
+
initializer_range=0.02,
|
| 204 |
+
rms_norm_eps=1e-05,
|
| 205 |
+
use_cache=True,
|
| 206 |
+
tie_word_embeddings=False,
|
| 207 |
+
rope_theta=1000000.0,
|
| 208 |
+
use_sliding_window=False,
|
| 209 |
+
sliding_window=4096,
|
| 210 |
+
max_window_layers=80,
|
| 211 |
+
attention_dropout=0.0,
|
| 212 |
+
vision_config=None,
|
| 213 |
+
rope_scaling=None,
|
| 214 |
+
**kwargs,
|
| 215 |
+
):
|
| 216 |
+
if isinstance(vision_config, dict):
|
| 217 |
+
self.vision_config = self.sub_configs["vision_config"](**vision_config)
|
| 218 |
+
elif vision_config is None:
|
| 219 |
+
self.vision_config = self.sub_configs["vision_config"]()
|
| 220 |
+
|
| 221 |
+
self.vocab_size = vocab_size
|
| 222 |
+
self.max_position_embeddings = max_position_embeddings
|
| 223 |
+
self.hidden_size = hidden_size
|
| 224 |
+
self.intermediate_size = intermediate_size
|
| 225 |
+
self.num_hidden_layers = num_hidden_layers
|
| 226 |
+
self.num_attention_heads = num_attention_heads
|
| 227 |
+
self.use_sliding_window = use_sliding_window
|
| 228 |
+
self.sliding_window = sliding_window
|
| 229 |
+
self.max_window_layers = max_window_layers
|
| 230 |
+
|
| 231 |
+
# for backward compatibility
|
| 232 |
+
if num_key_value_heads is None:
|
| 233 |
+
num_key_value_heads = num_attention_heads
|
| 234 |
+
|
| 235 |
+
self.num_key_value_heads = num_key_value_heads
|
| 236 |
+
self.hidden_act = hidden_act
|
| 237 |
+
self.initializer_range = initializer_range
|
| 238 |
+
self.rms_norm_eps = rms_norm_eps
|
| 239 |
+
self.use_cache = use_cache
|
| 240 |
+
self.rope_theta = rope_theta
|
| 241 |
+
self.attention_dropout = attention_dropout
|
| 242 |
+
self.rope_scaling = rope_scaling
|
| 243 |
+
|
| 244 |
+
# Validate the correctness of rotary position embeddings parameters
|
| 245 |
+
# BC: if there is a 'type' field, move it to 'rope_type'.
|
| 246 |
+
# and change type from 'mrope' to 'default' because `mrope` does default RoPE calculations
|
| 247 |
+
# one can set it to "linear"/"dynamic" etc. to have scaled RoPE
|
| 248 |
+
# TODO: @raushan update config in the hub
|
| 249 |
+
if self.rope_scaling is not None and "type" in self.rope_scaling:
|
| 250 |
+
if self.rope_scaling["type"] == "mrope":
|
| 251 |
+
self.rope_scaling["type"] = "default"
|
| 252 |
+
self.rope_scaling["rope_type"] = self.rope_scaling["type"]
|
| 253 |
+
rope_config_validation(self, ignore_keys={"mrope_section"})
|
| 254 |
+
|
| 255 |
+
super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
|
| 256 |
+
|
| 257 |
+
|
| 258 |
+
__all__ = ["Qwen2_5_VLConfig"]
|
decoder_81_512.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cefbd95494373fbb9c65c2be057f3968f2d7944d60e39e5b0d4ee037b6785f2
|
| 3 |
+
size 23929003150
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.1,
|
| 11 |
+
"top_k": 1,
|
| 12 |
+
"top_p": 0.001,
|
| 13 |
+
"transformers_version": "4.49.0"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed48777c36ab636d7a35fe5bab40ad7f3bb19d7f5e323bd0896f543f87f5a82
|
| 3 |
+
size 4968243304
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01074e2309f0ee0c52bcba4b1ec6e1d89c34f56941bfda8b260e43f7325cc12d
|
| 3 |
+
size 4991495816
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e316ffd964c01867b40f04099c9cd4d5339b71099465310a2020d38a2c8b30f
|
| 3 |
+
size 4932751040
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2b75187a66c1dcd450f8834bc2b66a803a1bb83e488d43086ceaa3a9624232f
|
| 3 |
+
size 1717614592
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,737 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16610023424
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"vision_head.weight": "model-00004-of-00004.safetensors",
|
| 346 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 347 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 349 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 351 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 353 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 355 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 359 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 361 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 363 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 365 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 367 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 371 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 373 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 375 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 377 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 379 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 383 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 385 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 387 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 389 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 391 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 395 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 397 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 399 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 401 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 403 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 406 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 407 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 408 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 409 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 429 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 441 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 453 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 465 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 477 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 487 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 499 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 501 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 511 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 523 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 547 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 559 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 561 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 571 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 583 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 595 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 607 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 619 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 643 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 655 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 667 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 679 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 691 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 703 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 715 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 717 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 729 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 731 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 732 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
| 733 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 734 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
| 735 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
| 736 |
+
}
|
| 737 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|