Hugging Face's logo

Wenboz
/
llama3-dpo-lora

PEFT
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
Model card Files Community
Wenboz commited on
Commit
df3d920
·
verified ·
1 Parent(s): 797a0f9

Training in progress, step 955

Browse files
Files changed (3) hide show
  1. adapter_config.json +4 -4
  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
  "k_proj",
 
24
  "q_proj",
25
- "down_proj",
26
- "gate_proj",
27
  "o_proj",
28
- "v_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "k_proj",
23
+ "up_proj",
24
  "q_proj",
 
 
25
  "o_proj",
26
+ "v_proj",
27
+ "gate_proj",
28
+ "down_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 sha256:520dcf941415e67d75a063b1727cdb49ea2edc37ce64d6f402e482044dc6f19b
3
  size 335605144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a45addc9f2cfce29b36fef15e7bcb6c0b867c4f0a6c3cbd079d68248e3d462e
3
  size 335605144
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be8289607a75716b1031b07545d388708e56058324bbf1ac12dbdbe437a76bd7
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd67a36f2c39dd7047e0f8b26c5247d27334b41cefb3736a9a22c0d9faf401cb
3
  size 5624