Hugging Face's logo

ale-bay
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
ale-bay commited on
Commit
ef664f4
•
1 Parent(s): fdadbc0

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +3 -3
  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
  "up_proj",
 
23
  "o_proj",
24
  "k_proj",
25
- "q_proj",
26
- "v_proj",
27
  "gate_proj",
28
- "down_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
20
  "revision": null,
21
  "target_modules": [
22
  "up_proj",
23
+ "v_proj",
24
  "o_proj",
25
  "k_proj",
 
 
26
  "gate_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 sha256:1171fe2836a5290b58eea6d5f2665c8fee1d9cb80725e2a1fb7aa474de6b5bcf
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa7ad6a4bf14891fe1726021076040629019db3c5ae0e20e233cf12bbf2e14e
3
  size 671150064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3cf8aa6be47845e82647cb3169580dedc51e6c45504409861b6a7ab89f8f094
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789f29f3d085b5548717849a815734f51f34b04baa4aa3a9338d63b2a7cdba7e
3
+ size 5112