Hugging Face's logo

axel-darmouni
/
qwen2.5_1.5b_coder_dslearn_os_rl

Transformers
Safetensors
Generated from Trainer
grpo
trl
Model card Files
xet
Community
axel-darmouni commited on
Commit
c0d6e82
·
verified ·
1 Parent(s): b0facc4

Training in progress, step 100

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: qwen2.5_1.5b_coder_dslearn_os_rl
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - grpo
 
9
  licence: license
10
  ---
11
 
 
4
  model_name: qwen2.5_1.5b_coder_dslearn_os_rl
5
  tags:
6
  - generated_from_trainer
 
7
  - grpo
8
+ - trl
9
  licence: license
10
  ---
11
 
adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "q_proj",
29
- "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "v_proj",
29
+ "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d242689d5534685a0c39b636f2161d028c231680daf2c6aa1c47f81dd4072c
3
  size 4373064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f7e378e39049896dd194d3300ab029bc064dd42c4fa3d68244cca5a33fda3b
3
  size 4373064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:945543bc06896ab95a0699a1ea29d622b3213f71bfbaa6faed61c086d024281b
3
  size 7800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1979b205bf141b53caf0bf3a758918795cfb1bc4f061094c8a2270e693e6ab5d
3
  size 7800