Hugging Face's logo

Holarissun
/
REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
Holarissun commited on
Commit
3c993a6
•
1 Parent(s): 3a3d05e

helpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Browse files
Files changed (3) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cc7be35e7ef86916dfd7ff03016ed19e1a5006dafa2111b26f1edc3a7742ff4
3
  size 14755192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b39e4110dd723e2155228308307b40befb39b04a492e829fc6b0b977804ef8d
3
  size 14755192
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b370f56ebeb910aa31e18bf24917da266e9d2fa12755b7c3b70c63126c0c15
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1023d2afddc5d037de7a7beb7dc3129467ebb8750d7d111bc718055691640cfe
3
  size 4984