Hugging Face's logo

shenxq
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
shenxq commited on
Commit
3ba2dc4
•
1 Parent(s): de0c06e

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +2 -2
  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
- "o_proj",
25
  "gate_proj",
 
26
  "down_proj",
27
- "q_proj",
28
- "up_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "up_proj",
 
 
23
  "gate_proj",
24
+ "k_proj",
25
  "down_proj",
26
+ "o_proj",
27
+ "v_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 sha256:6052991d04f63299b92ad5b7794163db85499e588fc3031f814a9877029dd414
3
- size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb01d9e4f6cd19165965e6e4b959cf9526e68503fdd05391a4316b1de74ad3a
3
+ size 83945744
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fee41ec1b45b86b78f6aa2bc1bd14d3332831518f258d69fa9acb1393bd5b3ed
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c10156d31210025a4a9a6a79a744c6f981f64befc21ca735eac8103863113f
3
  size 5176