Hugging Face's logo

minionKP
/
reward_model_output

PEFT
Safetensors
llama
trl
reward-trainer
Generated from Trainer
Model card Files Community
minionKP commited on
Commit
5f7b803
•
1 Parent(s): f725802

End of training

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
@@ -23,8 +23,8 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "q_proj",
27
- "v_proj"
28
  ],
29
  "task_type": "SEQ_CLS",
30
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "v_proj",
27
+ "q_proj"
28
  ],
29
  "task_type": "SEQ_CLS",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d345952712d72b67d257d8a79934aa1617a0d3302a0fec2aa293a9625d5a9597
3
  size 6841016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ffb054e7403e62db4c5576eef5fb69e99226d9a033a3689dd6658f41c636cb
3
  size 6841016
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02989f0cc2d65ce708a856ec5fe8cbcbcf73ee4946d508b101a7847ee3191779
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29275150d1269994247589da5597402e13cc2bfa8da41ed6f62cf1071faf1bf4
3
  size 6200