Hugging Face's logo

jikaixuan
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
jikaixuan commited on
Commit
834ad57
•
1 Parent(s): 04ab470

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 +2 -2
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "revision": null,
21
  "target_modules": [
22
  "k_proj",
23
- "up_proj",
24
  "o_proj",
25
- "q_proj",
26
  "gate_proj",
27
- "v_proj",
28
- "down_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
20
  "revision": null,
21
  "target_modules": [
22
  "k_proj",
23
+ "v_proj",
24
  "o_proj",
 
25
  "gate_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "up_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 sha256:242bee41488c3df56717669b7306bad61dde84d08f49624d2353261aa5f202b8
3
  size 83945744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae7f81708141f3846baf6c6e2e4e36f60a61f3ff47c1527bf7d5d85bf118fbd
3
  size 83945744
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96449288cd0c0f6f97aaf6903706a25976efeb59722e4ec2c2f1b63e9f73e8d
3
- size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc4e5dcb3ef08d7a371088bc04ccc10240a32b15ead5755a987f922ecc1b4b9
3
+ size 4856