Hugging Face's logo

merve
/
qwen3vl-2b-dpo-rlaif-1pct

Transformers
Safetensors
Generated from Trainer
dpo
trl
hf_jobs
Model card Files
xet
 Community
merve HF Staff commited on
Commit
c12fdf8
·
verified ·
1 Parent(s): bee2c11

Training in progress, step 141

Browse files
Files changed (3) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -30,9 +30,9 @@
30
  "revision": null,
31
  "target_modules": [
32
  "q_proj",
33
- "k_proj",
34
  "v_proj",
35
- "o_proj"
 
36
  ],
37
  "target_parameters": null,
38
  "task_type": "CAUSAL_LM",
 
30
  "revision": null,
31
  "target_modules": [
32
  "q_proj",
 
33
  "v_proj",
34
+ "o_proj",
35
+ "k_proj"
36
  ],
37
  "target_parameters": null,
38
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a279aae2840b76e630c0dffb8553a3cb3cfa8cf558d0c841435427d5d3061f9
3
  size 25723480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:437ffe49c98c9a5b7259006ddad10c9fa6d0dae4d6961a60d16af4284d0129b3
3
  size 25723480
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:159003ec2f13685165c3905302478924856db308dc5a3c0accd9cd6028ef62be
3
  size 6865
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9cec744f5ab600db6923d09ea912f7680521b2fda577c3416e42ce1e8b95a0
3
  size 6865