初始化项目，由ModelHub XC社区提供模型
Model: maveryn/trace-qwen2.5-vl-3b 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
|
||||
1
.trace_model_revision.json
Normal file
1
.trace_model_revision.json
Normal file
@@ -0,0 +1 @@
|
||||
{"file_count":15,"file_sha256":{"added_tokens.json":"58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b","chat_template.jinja":"a0bc6f6fc7a29a80017a433e8f03a1cc1236e838a944a2d034295a60c4f2fddb","config.json":"29cadee0bc6b4672ff1057537c853251a7b74345b3031c9d3624c1d2fefb10f4","generation_config.json":"ade5316c0962ced5772ab4317c0430758648e1993cd5c8386df03c0983d2f376","merges.txt":"8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5","model-00001-of-00002.safetensors":"2f5e423bd44bdd656a1c9d92fcf506c8b27145dce33a3ea0bf25afac844d513a","model-00002-of-00002.safetensors":"a5f27eb4839c0adb8ebf68d2ab8bf95a8d6f530e77b596c9f56769697b51c7de","model.safetensors.index.json":"66ebff9b20f47c1e72daa7c42661bd4b704b6b1710b6b41f83d4c314a113d1a1","preprocessor_config.json":"dfc7263fe735989c65c290d394198c4724d5afc58bf15c815d5e2e25b00b51b1","special_tokens_map.json":"76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd","tokenizer.json":"9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa","tokenizer_config.json":"f64d944a98d2d9901581be7a5f36b626ff2dc0d5b7d5dedb412412ca39606df0","trace_training_provenance.json":"5f4a617c67cba39f791e322f84c6c8e1f3df320abbe948b852e1b62e4a8b7b20","video_preprocessor_config.json":"15bb7c2f2bc95fe9cc3749a4b287872b4886a15e9fcf550a4122a46ae26150bd","vocab.json":"ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"},"immutable_revision":"sha256set:6f672d3df1f087347d73baf568b11360f8fc7779f507e7f6274b0691784c3f2b","model_origin":"local_registration","registered_at":"2026-07-17T11:17:38+00:00","schema_version":"trace-model-revision-v1","slug":"trace-qwen25vl3b-answer-step500-20260716","source":"maveryn/trace-qwen2.5-vl-3b@7b88f8a0e7e21aedb73c4e9a5ed891712c0a94d1"}
|
||||
150
README.md
Normal file
150
README.md
Normal file
@@ -0,0 +1,150 @@
|
||||
---
|
||||
license: other
|
||||
license_name: qwen-research
|
||||
license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-VL-3B-Instruct
|
||||
datasets:
|
||||
- maveryn/trace
|
||||
pipeline_tag: image-text-to-text
|
||||
library_name: transformers
|
||||
tags:
|
||||
- multimodal
|
||||
- visual-reasoning
|
||||
- reinforcement-learning
|
||||
- grpo
|
||||
- rlvr
|
||||
- trace
|
||||
---
|
||||
|
||||
# TRACE Qwen2.5-VL 3B
|
||||
|
||||
TRACE Qwen2.5-VL 3B is a GRPO checkpoint derived from
|
||||
[`Qwen/Qwen2.5-VL-3B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
|
||||
and trained on 64,000 grounded visual-reasoning examples spanning 1,000 tasks
|
||||
from
|
||||
[`maveryn/trace`](https://huggingface.co/datasets/maveryn/trace). This
|
||||
repository contains the merged step-500 inference checkpoint.
|
||||
|
||||
[Paper](https://arxiv.org/abs/2607.19790) ·
|
||||
[Project page](https://maveryn.github.io/trace/) ·
|
||||
[GitHub](https://github.com/maveryn/trace) ·
|
||||
[Collection](https://huggingface.co/collections/maveryn/trace-6a604291b4be4ed6399b9f24) ·
|
||||
[Training configuration](https://github.com/maveryn/trace/blob/rlvr/rlvr/configs/trace-qwen2.5-vl-3b.yaml) ·
|
||||
[Evaluation suite](https://github.com/maveryn/trace/tree/rlvr/rlvr/evaluation/trace_eval) ·
|
||||
[Run artifacts](https://huggingface.co/datasets/maveryn/trace-eval-runs)
|
||||
|
||||
## Training and provenance
|
||||
|
||||
| Field | Value |
|
||||
| --- | --- |
|
||||
| Base model | `Qwen/Qwen2.5-VL-3B-Instruct@66285546d2b821cf421d4f5eb2576359d3770cd3` |
|
||||
| Dataset | `maveryn/trace@4e5b54361360296a855542b40cfd8b7f81b355fe` |
|
||||
| Method | GRPO, 500 steps, global/rollout batch 128, 8 responses per prompt |
|
||||
| Optimization | AdamW, learning rate `1e-6`, constant schedule, KL disabled |
|
||||
| Reward | `0.95 × exact JSON answer + 0.05 × valid JSON format`; annotation reward `0` |
|
||||
| Reference run | 8 NVIDIA H100 80GB GPUs |
|
||||
| Released artifact | Merged step-500 inference weights |
|
||||
|
||||
The released training profile reads `prompt_answer`, scores `answer_gt`, and
|
||||
does not use the advisory `trace_supervision_mode` column. The consumed fields,
|
||||
embedded image bytes, and row order in the current dataset release were
|
||||
verified identical to the original training input in the public
|
||||
[equivalence receipt](https://github.com/maveryn/trace/blob/rlvr/rlvr/dataset_equivalence.v1.json).
|
||||
|
||||
The canonical output ends with `{"answer": ...}`. Exact hashes, source
|
||||
revision, and run provenance are recorded in
|
||||
[`trace_training_provenance.json`](trace_training_provenance.json) and
|
||||
[`.trace_model_revision.json`](.trace_model_revision.json). The repository
|
||||
does not include optimizer, scheduler, trainer, or FSDP state for continuation.
|
||||
|
||||
## Evaluation
|
||||
|
||||
`trace_eval_v1` evaluates 24 external benchmarks and 32,805 examples per model
|
||||
and decoding seed. Scores below are the unweighted macro mean of the 24
|
||||
benchmark percentages, reported as mean ± sample standard deviation across
|
||||
seeds 42, 43, and 44.
|
||||
|
||||
| Model | Overall score |
|
||||
| --- | ---: |
|
||||
| Qwen2.5-VL-3B-Instruct | 39.34 ± 0.63 |
|
||||
| TRACE Qwen2.5-VL 3B | **42.85 ± 0.39** |
|
||||
| Paired improvement | **+3.51 ± 0.25** |
|
||||
|
||||
Per-benchmark scores, model revisions, aggregation, and benchmark provenance
|
||||
are available in the public
|
||||
[`results.json`](https://github.com/maveryn/trace/blob/rlvr/rlvr/evaluation/trace_eval/results.json)
|
||||
and [evaluation documentation](https://github.com/maveryn/trace/blob/rlvr/rlvr/evaluation/trace_eval/README.md).
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
|
||||
|
||||
model_id = "maveryn/trace-qwen2.5-vl-3b"
|
||||
revision = "2ec2374d5c219e6b12e26bda93d3b3adeb1e30c5"
|
||||
image_url = "https://raw.githubusercontent.com/maveryn/trace/main/docs/assets/paper-domain-montage/trace-paper-domain-montage.png"
|
||||
|
||||
processor = AutoProcessor.from_pretrained(model_id, revision=revision)
|
||||
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
||||
model_id,
|
||||
revision=revision,
|
||||
dtype="auto",
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image", "url": image_url},
|
||||
{"type": "text", "text": "How many visual domains are shown with example images? Respond with only a JSON object using the key \"answer\"."},
|
||||
],
|
||||
}
|
||||
]
|
||||
inputs = processor.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_dict=True,
|
||||
return_tensors="pt",
|
||||
).to(model.device)
|
||||
output_ids = model.generate(**inputs, max_new_tokens=128)
|
||||
generated_ids = [
|
||||
output[len(prompt) :] for prompt, output in zip(inputs.input_ids, output_ids)
|
||||
]
|
||||
print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])
|
||||
```
|
||||
|
||||
### Verified reference answer
|
||||
|
||||
For the published montage used above, the expected output is:
|
||||
|
||||
```json
|
||||
{"answer": 11}
|
||||
```
|
||||
|
||||
The value is backed by the committed
|
||||
[montage manifest](https://github.com/maveryn/trace/blob/main/docs/gallery/paper-domain-montage.v1.json)
|
||||
(`layout.panel_count`). This is reference ground truth, not a claim about a
|
||||
particular decoding run; publish qualitative model outputs only with their
|
||||
recorded inference settings.
|
||||
|
||||
The pinned revision is the checkpoint used by the canonical evaluation; later
|
||||
repository heads may update documentation without changing the model weights.
|
||||
|
||||
## Intended use and limitations
|
||||
|
||||
This checkpoint is intended for research on multimodal reasoning and
|
||||
verifiable-reward post-training. It can produce incorrect answers,
|
||||
unsupported reasoning, or unreliable grounding. It was trained on synthetic
|
||||
tasks and has not been validated for safety-critical, medical, legal, or
|
||||
autonomous decision-making uses. Results depend on the recorded prompts,
|
||||
decoding, parsers, and scorers.
|
||||
|
||||
## License
|
||||
|
||||
This checkpoint is subject to the upstream
|
||||
[Qwen Research License](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE).
|
||||
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
|
||||
}
|
||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
||||
You are a helpful assistant.<|im_end|>
|
||||
{% endif %}<|im_start|>{{ message['role'] }}
|
||||
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
||||
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
||||
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
||||
{% endif %}
|
||||
139
config.json
Normal file
139
config.json
Normal file
@@ -0,0 +1,139 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"text_config": {
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2_5_vl_text",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 151936
|
||||
},
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"dtype": "float32",
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3420,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_heads": 16,
|
||||
"out_hidden_size": 2048,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"tokens_per_second": 2,
|
||||
"window_size": 112
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f5e423bd44bdd656a1c9d92fcf506c8b27145dce33a3ea0bf25afac844d513a
|
||||
size 4963150776
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a5f27eb4839c0adb8ebf68d2ab8bf95a8d6f530e77b596c9f56769697b51c7de
|
||||
size 3168517200
|
||||
833
model.safetensors.index.json
Normal file
833
model.safetensors.index.json
Normal file
@@ -0,0 +1,833 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 4065787904,
|
||||
"total_size": 8131575808
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00002-of-00002.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
39
preprocessor_config.json
Normal file
39
preprocessor_config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"pad_size": null,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
209
tokenizer_config.json
Normal file
209
tokenizer_config.json
Normal file
@@ -0,0 +1,209 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"use_fast": true
|
||||
}
|
||||
16
trace_training_provenance.json
Normal file
16
trace_training_provenance.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"base_model": "Qwen/Qwen2.5-VL-3B-Instruct",
|
||||
"base_revision": "66285546d2b821cf421d4f5eb2576359d3770cd3",
|
||||
"checkpoint_retention": 1,
|
||||
"checkpoint_step": 500,
|
||||
"dataset": "maveryn/trace",
|
||||
"dataset_revision": "e317b746b258630682367cc6a9d87dedd195113c",
|
||||
"merged_safetensor_sha256": {
|
||||
"model-00001-of-00002.safetensors": "2f5e423bd44bdd656a1c9d92fcf506c8b27145dce33a3ea0bf25afac844d513a",
|
||||
"model-00002-of-00002.safetensors": "a5f27eb4839c0adb8ebf68d2ab8bf95a8d6f530e77b596c9f56769697b51c7de"
|
||||
},
|
||||
"published_at": "2026-07-17T11:16:28.752750+00:00",
|
||||
"run_name": "trace_qwen25vl3b_easyr1_all1000_answer_nokl_step500_bsz128_rollout8_iidval2000_rerun_20260716T225857Z",
|
||||
"source_commit": "847e9f5279f8111fdbfef1c8b8631fc621c23456",
|
||||
"wandb_url": "https://wandb.ai/llm-reasoning-rl/trace_easyr1/runs/kijsydl8"
|
||||
}
|
||||
43
video_preprocessor_config.json
Normal file
43
video_preprocessor_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": false,
|
||||
"fps": null,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_frames": 768,
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"min_pixels": 3136,
|
||||
"num_frames": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "Qwen2VLVideoProcessor"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user