Hugging Face's logo

shenxq
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
shenxq commited on
Commit
1496b58
•
1 Parent(s): 7405978

Training in progress, step 1200

Browse files
Files changed (3) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +2 -2
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,12 +19,12 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "gate_proj",
23
- "k_proj",
24
  "v_proj",
25
- "q_proj",
26
- "down_proj",
27
  "o_proj",
 
 
 
28
  "up_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "v_proj",
23
+ "k_proj",
 
24
  "o_proj",
25
+ "gate_proj",
26
+ "down_proj",
27
+ "q_proj",
28
  "up_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc58a16a9c7cd2f28d8d73ee185e2a29e281ee67b6448aa7e42894ff5183ba99
3
- size 83945744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2dd2e91042c567a32a1c3c899b935d5f131e1c96db23724c115eaa43d29e62
3
+ size 167832240
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:387786aa767b34abf9b422cc0cdb3b0676810f6854c743acf6d68e01b38091c3
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee41ec1b45b86b78f6aa2bc1bd14d3332831518f258d69fa9acb1393bd5b3ed
3
  size 5176