Hugging Face's logo

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

PEFT
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
Model card Files
xet
Community
shenxq commited on
Commit
98582ec
·
verified ·
1 Parent(s): 04735c1

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +2 -2
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "revision": null,
21
  "target_modules": [
22
  "up_proj",
 
23
  "k_proj",
24
- "q_proj",
25
  "gate_proj",
 
26
  "down_proj",
27
- "o_proj",
28
- "v_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
20
  "revision": null,
21
  "target_modules": [
22
  "up_proj",
23
+ "o_proj",
24
  "k_proj",
 
25
  "gate_proj",
26
+ "v_proj",
27
  "down_proj",
28
+ "q_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:e69e737e1c3cc31220e7a34f1ac3283e4715c26d80bbca276c7e216632134c7a
3
- size 671149616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480d7f57a9e1d4fe6e21e6078899454431e13bd54389cd094520d4c5abe64b1e
3
+ size 671150064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dba90a61d17c20170c4a9f8b6467ce27aa0e04d5e569a273341ec5e2e86d7739
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e29821130f6a01ec02a0208dadb72a32050a4ec36ede0382a8dc551b1870a5e
3
  size 5112