Hugging Face's logo

nomadrp
/
dpo_model

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
nomadrp commited on
Commit
e6990ce
•
1 Parent(s): d112060

Training in progress, step 500

Browse files
Files changed (2) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "k_proj",
24
- "q_proj",
25
  "o_proj",
26
- "v_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
  "k_proj",
 
25
  "o_proj",
26
+ "q_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:caf131ac357043d723d26d360725f67b216add5d9834b47f561c7f52972e304f
3
  size 218138576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d59aa9c7b1c5fb74a3319d8c34996e519a292825671864cff0568eb937f33531
3
  size 218138576