Hugging Face's logo

swadeshb
/
Llama-3.2-3B-Instruct-TRACE_GRPO-V15

Transformers
Safetensors
Generated from Trainer
trl
grpo
Model card Files
xet
 Community
swadeshb commited on
Commit
a78fa2a
·
verified ·
1 Parent(s): 4c96531

Training in progress, step 100

Browse files
Files changed (4) hide show
  1. README.md +2 -2
  2. adapter_config.json +4 -4
  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: Llama-3.2-3B-Instruct-TRACE_GRPO-V15
5
  tags:
6
  - generated_from_trainer
7
- - grpo
8
  - trl
 
9
  licence: license
10
  ---
11
 
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/swadeshb-individual/huggingface/runs/lwz7k09n)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
4
  model_name: Llama-3.2-3B-Instruct-TRACE_GRPO-V15
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
+ - grpo
9
  licence: license
10
  ---
11
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/swadeshb-individual/huggingface/runs/vd9rlzwm)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
adapter_config.json CHANGED
@@ -25,13 +25,13 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "k_proj",
29
  "up_proj",
30
- "v_proj",
31
  "gate_proj",
32
  "down_proj",
33
- "q_proj",
34
- "o_proj"
 
35
  ],
36
  "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
28
  "up_proj",
29
+ "k_proj",
30
  "gate_proj",
31
  "down_proj",
32
+ "o_proj",
33
+ "v_proj",
34
+ "q_proj"
35
  ],
36
  "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00408bde873c4e680054f2a4a206eca0366258b7f3056e41b8cfb16d9b7eb621
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4a976c84306e7a89acdb0e53b5784da0994fd857bb77b7287e517887944c61
3
  size 97307544
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18acb3385fe5f0bca9d2718fe97663a904ecdf09de42ac5181d0d57da1576911
3
  size 7377
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8853363e908c812558c1efc2186adab56ca577621f6fef839c990d3b2d172a3
3
  size 7377