weathon commited on
Commit
d9669ff
·
verified ·
1 Parent(s): 15b398a

Training in progress, step 300

Browse files
README.md CHANGED
@@ -1,17 +1,17 @@
1
  ---
2
- base_model: Qwen/Qwen2.5-VL-7B-Instruct
3
  library_name: transformers
4
  model_name: anti_aesthetics_captioning
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - sft
 
9
  licence: license
10
  ---
11
 
12
  # Model Card for anti_aesthetics_captioning
13
 
14
- This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/4n52rfyh)
31
 
32
 
33
  This model was trained with SFT.
 
1
  ---
2
+ base_model: Qwen/Qwen2.5-VL-3B-Instruct
3
  library_name: transformers
4
  model_name: anti_aesthetics_captioning
5
  tags:
6
  - generated_from_trainer
 
7
  - sft
8
+ - trl
9
  licence: license
10
  ---
11
 
12
  # Model Card for anti_aesthetics_captioning
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/dvmegrnl)
31
 
32
 
33
  This model was trained with SFT.
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
@@ -25,11 +25,12 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "k_proj",
29
- "o_proj",
30
  "qkv",
 
 
 
31
  "v_proj",
32
- "q_proj"
33
  ],
34
  "target_parameters": null,
35
  "task_type": "CAUSAL_LM",
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
28
  "qkv",
29
+ "o_proj",
30
+ "q_proj",
31
+ "proj",
32
  "v_proj",
33
+ "k_proj"
34
  ],
35
  "target_parameters": null,
36
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bdfb664c5388185befa82c1187f73b4d36ad63a391a4857e0142f722b46fc19
3
- size 203466072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b285e4ae823770b6204b9a7ab69701429c19924f0a6877ee5413ee8a735523
3
+ size 181568928
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed701b2b37e1bca68597c2d604aee0f225b006e0ed7e46fcbd34bee44b9a8e60
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40f1721f2a7c54e0ced2f9cefdc6dadf3ec54e407401f6efc56c7501aca229e
3
  size 5777