jxiao986 commited on
Commit
11bbf15
·
verified ·
1 Parent(s): f26b975

jxiao986/dpo-mistral7b-lima

Browse files
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/1062983729-hong-kong-university-of-science-and-technology/huggingface/runs/zsruni1u)
31
 
32
 
33
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/1062983729-hong-kong-university-of-science-and-technology/huggingface/runs/upgv1a1p)
31
 
32
 
33
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
adapter_config.json CHANGED
@@ -24,13 +24,10 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "v_proj",
28
- "o_proj",
29
- "gate_proj",
30
  "k_proj",
31
- "q_proj",
32
- "down_proj",
33
- "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
 
 
 
27
  "k_proj",
28
+ "o_proj",
29
+ "v_proj",
30
+ "q_proj"
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf058a542385f8a1532880de1badf1b49ccfcf77bf9decd23020b7d9caeba612
3
- size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f88386f61f16fe5f72ef2a1900b1284148e6ac0f3e9e262e1f80a8770aa24ee
3
+ size 109086416
runs/May10_16-55-38_620413a29def/events.out.tfevents.1746896140.620413a29def.16974.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6001fc9784a4870dd98dd45e87bf4cfcc9b8688244801287b4082792995ec1e1
3
+ size 8020
runs/May10_17-08-56_620413a29def/events.out.tfevents.1746896937.620413a29def.24265.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a79eaa1b3b669f172284955e8ae8d6b6aecf698bd506aa78255618982592a5f
3
+ size 6690
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a077c44ae0f84a089b7a543a5f8c567eb4a5abf105294ecafae3f8e49e720c
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d489cd94509a5ec088152a324a270d1f06f51946d1ecc36133a14c1f1e8a2052
3
  size 6200