nbeerbower / Hemlock2-Coder-7B-GRPO

huggingface.co
Total runs: 35
24-hour runs: 0
7-day runs: 1
30-day runs: -21
Model's Last Updated: July 15 2026
reinforcement-learning

Introduction of Hemlock2-Coder-7B-GRPO

Model Details of Hemlock2-Coder-7B-GRPO

Hemlock2-Coder-7B-GRPO

hemlang/Hemlock2-Coder-7B improved with execution-reward GRPO ( grimoire ≥ 2.0 / hemlock-rl ). Completions were executed in the Hemlock interpreter's sandbox and rewarded for exactly reproducing verified reference stdout.

Strictly improves the base model on hembench (zero-shot, n=5, benchmark-overlapping training tasks held out):

pass@1 pass@5
Hemlock2-Coder-7B 28.9% 55.3%
Hemlock2-Coder-7B-GRPO 36.8% (+7.9) 57.9% (+2.6)

Largest gains in syntax (L1 pass@1 2/9 → 4/9, pass@5 7/9 → 8/9) and systems/concurrency (L4 pass@1 1/7 → 3/7).

Training
  • Method : GRPO (LoRA r=16 α=32, β=0.1 KL vs frozen base, G=8, dynamic sampling, unscaled advantages), 186 deduplicated prompts × 3 epochs.
  • Rewards : sandboxed execution; exact stdout match vs verified reference = 2.0, runs-but-wrong = 0.5, error = −0.5, no code / timeout = −1.0.
  • Data : execution-verified translation/generation tasks (now published as hemlang/hemlock-codex3-SFT ), one language-variant per task, hembench-name-overlapping tasks excluded.

Q8_0 GGUF included.

Runs of nbeerbower Hemlock2-Coder-7B-GRPO on huggingface.co

35
Total runs
0
24-hour runs
-5
3-day runs
1
7-day runs
-21
30-day runs

More Information About Hemlock2-Coder-7B-GRPO huggingface.co Model

More Hemlock2-Coder-7B-GRPO license Visit here:

https://choosealicense.com/licenses/apache-2.0

Hemlock2-Coder-7B-GRPO huggingface.co

Hemlock2-Coder-7B-GRPO huggingface.co is an AI model on huggingface.co that provides Hemlock2-Coder-7B-GRPO's model effect (), which can be used instantly with this nbeerbower Hemlock2-Coder-7B-GRPO model. huggingface.co supports a free trial of the Hemlock2-Coder-7B-GRPO model, and also provides paid use of the Hemlock2-Coder-7B-GRPO. Support call Hemlock2-Coder-7B-GRPO model through api, including Node.js, Python, http.

Hemlock2-Coder-7B-GRPO huggingface.co Url

https://huggingface.co/nbeerbower/Hemlock2-Coder-7B-GRPO

nbeerbower Hemlock2-Coder-7B-GRPO online free

Hemlock2-Coder-7B-GRPO huggingface.co is an online trial and call api platform, which integrates Hemlock2-Coder-7B-GRPO's modeling effects, including api services, and provides a free online trial of Hemlock2-Coder-7B-GRPO, you can try Hemlock2-Coder-7B-GRPO online for free by clicking the link below.

nbeerbower Hemlock2-Coder-7B-GRPO online free url in huggingface.co:

https://huggingface.co/nbeerbower/Hemlock2-Coder-7B-GRPO

Hemlock2-Coder-7B-GRPO install

Hemlock2-Coder-7B-GRPO is an open source model from GitHub that offers a free installation service, and any user can find Hemlock2-Coder-7B-GRPO on GitHub to install. At the same time, huggingface.co provides the effect of Hemlock2-Coder-7B-GRPO install, users can directly use Hemlock2-Coder-7B-GRPO installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Hemlock2-Coder-7B-GRPO install url in huggingface.co:

https://huggingface.co/nbeerbower/Hemlock2-Coder-7B-GRPO

Url of Hemlock2-Coder-7B-GRPO

Hemlock2-Coder-7B-GRPO huggingface.co Url

Provider of Hemlock2-Coder-7B-GRPO huggingface.co

nbeerbower
ORGANIZATIONS

Other API from nbeerbower

huggingface.co

Total runs: 87
Run Growth: 23
Growth Rate: 26.44%
Updated:February 05 2024