Hugging Face's logo

PhilSad
/
lucie-7b-GRPO-science-long-thinking-boxed-accuracy

Safetensors
Model card Files
xet
 Community
PhilSad commited on
Commit
aa81059
·
verified ·
1 Parent(s): 57ee0f3

Training in progress, step 10

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
@@ -24,8 +24,8 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "v_proj",
28
- "q_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "q_proj",
28
+ "v_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c2edc88fc402f77cde439e2a96857fd3e2d3d5ef60524e6ba21f3c27f0b4140
3
  size 13648432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010791769e286155e6fb41dde94d9ef83d5570db2159665ba995de235772d594
3
  size 13648432
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f4c0e276c1df6ac0e408009ad4efa4350d6c8e9e95832279f11fead1a87a265
3
  size 6865
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77ac39aed8b168d4f29c7f332ab5cd26bfd2195b987329b8976448c2e33407d
3
  size 6865