Hugging Face's logo

Wenboz
/
llama3-wpo-lora

PEFT
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
Model card Files Community
Wenboz commited on
Commit
669c4f7
•
1 Parent(s): 18bf707

Training in progress, step 955

Browse files
Files changed (3) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "k_proj",
23
- "v_proj",
24
- "gate_proj",
25
  "q_proj",
26
  "o_proj",
27
- "up_proj",
28
- "down_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "up_proj",
 
 
23
  "q_proj",
24
  "o_proj",
25
+ "down_proj",
26
+ "k_proj",
27
+ "gate_proj",
28
+ "v_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0758ac6b1ad069501cd9bae9794f24bbdba8988a4dc772b5b5b16d6fe39f5501
3
  size 335605144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60162cefe1bdce8c31fe195cac8fff5c9c6bc393daec3e7de1edf94b29e690a8
3
  size 335605144
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e83b7238325d2ef9c494bb65d32b30fff2d09b8a028e554992823b1a2dc1d91
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f761de1327710597ae5285a493c0d8e31be049a08b86d304577746dcc67aa5
3
  size 5688