初始化项目，由ModelHub XC社区提供模型
Model: Frywind/qwen-7b-0722-asft Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen2.5-VL-7B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: mix_0722
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# mix_0722
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the mixed_all dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-05
|
||||
- train_batch_size: 4
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 64
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 3.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.49.0
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.6.0
|
||||
- Tokenizers 0.21.1
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.9397590361445785,
|
||||
"total_flos": 4.737549008539484e+17,
|
||||
"train_loss": 0.6231146188286262,
|
||||
"train_runtime": 2388.9222,
|
||||
"train_samples_per_second": 3.327,
|
||||
"train_steps_per_second": 0.051
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"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 %}"
|
||||
}
|
||||
65
config.json
Normal file
65
config.json
Normal file
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"intermediate_size": 3420,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_heads": 16,
|
||||
"out_hidden_size": 3584,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"tokens_per_second": 2,
|
||||
"torch_dtype": "bfloat16",
|
||||
"window_size": 112
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 1e-06,
|
||||
"transformers_version": "4.51.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f92fd27948cceef3f2df722eb3acb00709b0517fea03fc255b1ae83c485d862
|
||||
size 1353142032
|
||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cef4991ba4794999e54c313e1c312ef6cb82a2dd6d463391e5d9446b5c19e214
|
||||
size 1886423520
|
||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d1abeca67af6c096a8625b0cbddeac9d213ae029c173630a00bb200fa278133d
|
||||
size 1864467800
|
||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c8d1a4bea09569fe06c8830a629220c8a49733dfa6d88b4b8ae97efa3c555b08
|
||||
size 1864467800
|
||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7679494fda0d4d1238ed201b3b469337b0378c9cf48df17ccdd66b0632c0c502
|
||||
size 1864467824
|
||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:760f26f21de1787a55d2b3a0a9fcbd75ca0c1eddec3223f2f983905b4b8fd69f
|
||||
size 1864467848
|
||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:34605a202471b89c0c759047ff5229531542e06419a2c2347d7ff121fb781565
|
||||
size 1864467848
|
||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:057d21593ddfed8f41085a8387bfc38f5f8888435a7972fc1c6a148fd93d1b68
|
||||
size 1864467848
|
||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:62c17b7b369bd417f92e5d9efbed686c79d2d7ee9e2f36311cda848906225abc
|
||||
size 1068046456
|
||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5a82546b2632145d269e6ab21c52bc101b21fb4e43b08b389b267a1177b1b6c
|
||||
size 1089994880
|
||||
736
model.safetensors.index.json
Normal file
736
model.safetensors.index.json
Normal file
@@ -0,0 +1,736 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16584333312
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00010-of-00010.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.norm.weight": "model-00009-of-00010.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00001-of-00010.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00010.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00010.safetensors"
|
||||
}
|
||||
}
|
||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
210
tokenizer_config.json
Normal file
210
tokenizer_config.json
Normal file
@@ -0,0 +1,210 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"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 %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.9397590361445785,
|
||||
"total_flos": 4.737549008539484e+17,
|
||||
"train_loss": 0.6231146188286262,
|
||||
"train_runtime": 2388.9222,
|
||||
"train_samples_per_second": 3.327,
|
||||
"train_steps_per_second": 0.051
|
||||
}
|
||||
13
trainer_log.jsonl
Normal file
13
trainer_log.jsonl
Normal file
@@ -0,0 +1,13 @@
|
||||
{"current_steps": 10, "total_steps": 123, "loss": 1.081, "lr": 7.692307692307694e-06, "epoch": 0.24096385542168675, "percentage": 8.13, "elapsed_time": "0:03:13", "remaining_time": "0:36:21"}
|
||||
{"current_steps": 20, "total_steps": 123, "loss": 0.8009, "lr": 9.900412805461968e-06, "epoch": 0.4819277108433735, "percentage": 16.26, "elapsed_time": "0:06:25", "remaining_time": "0:33:06"}
|
||||
{"current_steps": 30, "total_steps": 123, "loss": 0.7773, "lr": 9.422164654989073e-06, "epoch": 0.7228915662650602, "percentage": 24.39, "elapsed_time": "0:09:33", "remaining_time": "0:29:37"}
|
||||
{"current_steps": 40, "total_steps": 123, "loss": 0.7559, "lr": 8.585659023794818e-06, "epoch": 0.963855421686747, "percentage": 32.52, "elapsed_time": "0:12:42", "remaining_time": "0:26:21"}
|
||||
{"current_steps": 50, "total_steps": 123, "loss": 0.5987, "lr": 7.45866462322802e-06, "epoch": 1.1927710843373494, "percentage": 40.65, "elapsed_time": "0:15:46", "remaining_time": "0:23:02"}
|
||||
{"current_steps": 60, "total_steps": 123, "loss": 0.5907, "lr": 6.132483837128823e-06, "epoch": 1.4337349397590362, "percentage": 48.78, "elapsed_time": "0:18:54", "remaining_time": "0:19:51"}
|
||||
{"current_steps": 70, "total_steps": 123, "loss": 0.5766, "lr": 4.71455594568616e-06, "epoch": 1.6746987951807228, "percentage": 56.91, "elapsed_time": "0:22:03", "remaining_time": "0:16:41"}
|
||||
{"current_steps": 80, "total_steps": 123, "loss": 0.5707, "lr": 3.319753033922849e-06, "epoch": 1.9156626506024095, "percentage": 65.04, "elapsed_time": "0:25:10", "remaining_time": "0:13:31"}
|
||||
{"current_steps": 90, "total_steps": 123, "loss": 0.4834, "lr": 2.061073738537635e-06, "epoch": 2.144578313253012, "percentage": 73.17, "elapsed_time": "0:28:14", "remaining_time": "0:10:21"}
|
||||
{"current_steps": 100, "total_steps": 123, "loss": 0.4311, "lr": 1.0404887703886252e-06, "epoch": 2.3855421686746987, "percentage": 81.3, "elapsed_time": "0:31:21", "remaining_time": "0:07:12"}
|
||||
{"current_steps": 110, "total_steps": 123, "loss": 0.441, "lr": 3.406798539427386e-07, "epoch": 2.6265060240963853, "percentage": 89.43, "elapsed_time": "0:34:32", "remaining_time": "0:04:04"}
|
||||
{"current_steps": 120, "total_steps": 123, "loss": 0.4362, "lr": 1.834134568654333e-08, "epoch": 2.8674698795180724, "percentage": 97.56, "elapsed_time": "0:37:40", "remaining_time": "0:00:56"}
|
||||
{"current_steps": 123, "total_steps": 123, "epoch": 2.9397590361445785, "percentage": 100.0, "elapsed_time": "0:39:48", "remaining_time": "0:00:00"}
|
||||
126
trainer_state.json
Normal file
126
trainer_state.json
Normal file
@@ -0,0 +1,126 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.9397590361445785,
|
||||
"eval_steps": 500,
|
||||
"global_step": 123,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.24096385542168675,
|
||||
"grad_norm": 3.629333972930908,
|
||||
"learning_rate": 7.692307692307694e-06,
|
||||
"loss": 1.081,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.4819277108433735,
|
||||
"grad_norm": 2.5671825408935547,
|
||||
"learning_rate": 9.900412805461968e-06,
|
||||
"loss": 0.8009,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.7228915662650602,
|
||||
"grad_norm": 2.330085277557373,
|
||||
"learning_rate": 9.422164654989073e-06,
|
||||
"loss": 0.7773,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.963855421686747,
|
||||
"grad_norm": 2.4446911811828613,
|
||||
"learning_rate": 8.585659023794818e-06,
|
||||
"loss": 0.7559,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 1.1927710843373494,
|
||||
"grad_norm": 2.232125997543335,
|
||||
"learning_rate": 7.45866462322802e-06,
|
||||
"loss": 0.5987,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 1.4337349397590362,
|
||||
"grad_norm": 2.0914366245269775,
|
||||
"learning_rate": 6.132483837128823e-06,
|
||||
"loss": 0.5907,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 1.6746987951807228,
|
||||
"grad_norm": 1.837985873222351,
|
||||
"learning_rate": 4.71455594568616e-06,
|
||||
"loss": 0.5766,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 1.9156626506024095,
|
||||
"grad_norm": 2.1364665031433105,
|
||||
"learning_rate": 3.319753033922849e-06,
|
||||
"loss": 0.5707,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 2.144578313253012,
|
||||
"grad_norm": 1.9006352424621582,
|
||||
"learning_rate": 2.061073738537635e-06,
|
||||
"loss": 0.4834,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 2.3855421686746987,
|
||||
"grad_norm": 1.8541189432144165,
|
||||
"learning_rate": 1.0404887703886252e-06,
|
||||
"loss": 0.4311,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 2.6265060240963853,
|
||||
"grad_norm": 1.9577722549438477,
|
||||
"learning_rate": 3.406798539427386e-07,
|
||||
"loss": 0.441,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 2.8674698795180724,
|
||||
"grad_norm": 1.6799449920654297,
|
||||
"learning_rate": 1.834134568654333e-08,
|
||||
"loss": 0.4362,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 2.9397590361445785,
|
||||
"step": 123,
|
||||
"total_flos": 4.737549008539484e+17,
|
||||
"train_loss": 0.6231146188286262,
|
||||
"train_runtime": 2388.9222,
|
||||
"train_samples_per_second": 3.327,
|
||||
"train_steps_per_second": 0.051
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 123,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 1000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 4.737549008539484e+17,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:848d94434dd5a900ab486084859dc57a0309a4f73015035d53a0f50a33e1edc4
|
||||
size 7352
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user