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
xet
Metrics Community
jikaixuan commited on
Commit
f7c95fc
·
verified ·
1 Parent(s): 3bfa5b1

Training in progress, step 400

Browse files
Files changed (3) hide show
  1. adapter_config.json +3 -3
  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
- "up_proj",
23
- "v_proj",
24
  "q_proj",
25
  "gate_proj",
 
 
26
  "down_proj",
27
  "o_proj",
28
- "k_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "q_proj",
23
  "gate_proj",
24
+ "up_proj",
25
+ "k_proj",
26
  "down_proj",
27
  "o_proj",
28
+ "v_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:a786e5ec0ab52db3e851be16a8827974514f54f3067b52160981332ac1e67596
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce4df4dc5e3aa4b64020ce42957d629bc8c008a3148405c9a08f59a07e20cb9
3
  size 671150064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ae9269821a7a76bfccee733cea8c3af1d1b7b751ef31fb40915f4d080f4944
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9de8831bf203a26c117251200a242a486dd5bc4f1aae373c17a996f39be3288
3
  size 4920