Hugging Face's logo

winnieyangwannan
/
Yi-6B-Chat_honest_lying_dpo_to_lie_lora_True

Transformers
Safetensors
Generated from Trainer
Yi-6B-Chat
honest_lying
dpo_to_lie
lora_True
trl
dpo
Inference Endpoints
Model card Files Community
winnieyangwannan commited on
Commit
f091a9f
·
verified ·
1 Parent(s): 28e05a4

Training in progress, step 500

Browse files
Files changed (3) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "q_proj",
27
- "up_proj",
28
- "o_proj",
29
  "down_proj",
 
30
  "v_proj",
31
- "k_proj",
32
- "gate_proj"
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "k_proj",
 
 
27
  "down_proj",
28
+ "q_proj",
29
  "v_proj",
30
+ "up_proj",
31
+ "gate_proj",
32
+ "o_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3457d7fada02834b33e280ac583730d3ac725a941c7d7bc16bf402d8fc1b0411
3
  size 145287696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca3ec8029f2eff475959e631240f9abca6cd351aa3e460fd63f3298a616b690
3
  size 145287696
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:202cb9ee822152ed1049e91d1fbd760e2c9f4660c95cd6a99202d31feedbc751
3
  size 6456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c1d992cd018e5f37f5fa12c992cf175ef3802744527307e29ad0f0207972de
3
  size 6456