Hugging Face's logo

haizhongzheng
/
Llama-3.2-1B-dpo-lora

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
haizhongzheng commited on
Commit
217d6e0
•
1 Parent(s): 731af0a

Model save

Browse files
Files changed (2) hide show
  1. adapter_config.json +5 -5
  2. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "up_proj",
25
- "v_proj",
26
  "down_proj",
27
- "q_proj",
28
  "o_proj",
29
- "gate_proj"
 
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "down_proj",
 
24
  "o_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "gate_proj",
28
+ "q_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fda9e7497142062b2b46d1f8e9471fe9f7afd88e3c2a210330feb24a8bbe3e5
3
  size 6328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19eeb8238e8e0a90e8b5e34634739fa0145c33178cd3c4d2436ce1ed37c14050
3
  size 6328