Hugging Face's logo

shenxq
/
zephyr-7b-dpo-qlora-pairrm

PEFT
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Community
shenxq commited on
Commit
951dac4
•
1 Parent(s): 193ff66

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +4 -4
  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
- "v_proj",
23
- "k_proj",
24
  "q_proj",
 
 
25
  "o_proj",
26
  "up_proj",
27
- "down_proj",
28
- "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "q_proj",
23
+ "k_proj",
24
+ "v_proj",
25
  "o_proj",
26
  "up_proj",
27
+ "gate_proj",
28
+ "down_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:f66dedcfa579dcdfb9f1d78c397d7645e70f57c173df9dd20bfc82911ce23de6
3
  size 1342238560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3350354bd014755ace1c204742f15027b9a781bb3240f349b110bbde7dcc3f2b
3
  size 1342238560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3cba20d79f1f449940dbf2000bc1e4e4e0b02993915f88637775ed2674e361b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c2cff2b54f22db8d5004bd203c66a394845c52d92ef4ef5fd5aad267800542
3
  size 5176