Hugging Face's logo

NanQiangHF
/
llama3.1_8b_dpo_bwgenerator

PEFT
Safetensors
llama
trl
dpo
Generated from Trainer
Model card Files Community
NanQiangHF commited on
Commit
f498fa5
•
1 Parent(s): 086d365

llama3.1_8b_dpo_bwgenerator

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
@@ -22,8 +22,8 @@
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
- "v_proj",
26
- "q_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
+ "q_proj",
26
+ "v_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:629a1eee04ea88564ec1f8336e1521b9b707e76ff5d5014d054a2342fe446c99
3
  size 6832728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986334309f6778e864701a1af204ce18c2118f41243f2a307b46bd2fc7f2c279
3
  size 6832728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfbf000b1cc7f59d1dd674475b76799df7539ec05b1bfab64cf7ea66781d41f7
3
  size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc23bb38c1b3a7039a5b6c605d6d35b32a2c2aec9a91a77ebc363042e19ce7d
3
  size 6072