Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-iter-0

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
lole25 commited on
Commit
b3fdd14
•
1 Parent(s): b7f9dd9

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v_proj",
23
- "q_proj",
24
  "dense",
25
- "k_proj"
 
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "dense",
23
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4ae07661d1279e5c3b28a0ae048008ebcbde5b374e9a038b4624c66027a5365
3
  size 41977616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a91970ad32fd59ca792aa2083a2c74b90dac687a074c2c49e8e55236c0a2c0
3
  size 41977616
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f50f7272b242cdd13b152fddf5c5e4bc36c5357f58d76c31c590147921fafd0
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad796a191a97e0c1a72305d8c576efec65712b90fcf4d44483703b60c06b87a4
3
  size 5816