Instructions to use nbeerbower/Hemlock2-Coder-7B-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nbeerbower/Hemlock2-Coder-7B-GRPO with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0
# Run inference directly in the terminal:
llama cli -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0
# Run inference directly in the terminal:
llama cli -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Use Docker

docker model run hf.co/nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

LM Studio
Jan
Ollama
How to use nbeerbower/Hemlock2-Coder-7B-GRPO with Ollama:
```
ollama run hf.co/nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0
```

Unsloth Studio

How to use nbeerbower/Hemlock2-Coder-7B-GRPO with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nbeerbower/Hemlock2-Coder-7B-GRPO to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nbeerbower/Hemlock2-Coder-7B-GRPO to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nbeerbower/Hemlock2-Coder-7B-GRPO to start chatting

How to use nbeerbower/Hemlock2-Coder-7B-GRPO with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nbeerbower/Hemlock2-Coder-7B-GRPO with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use nbeerbower/Hemlock2-Coder-7B-GRPO with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use nbeerbower/Hemlock2-Coder-7B-GRPO with Docker Model Runner:
```
docker model run hf.co/nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0
```

Lemonade

How to use nbeerbower/Hemlock2-Coder-7B-GRPO with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nbeerbower/Hemlock2-Coder-7B-GRPO:Q8_0

Run and chat with the model

lemonade run user.Hemlock2-Coder-7B-GRPO-Q8_0

List all available models

lemonade list

Hemlock2-Coder-7B-GRPO / README.md

nbeerbower

Upload README.md with huggingface_hub

03c5b1d verified 17 days ago

preview code

Raw

History Blame Contribute Delete

1.58 kB

metadata

license: apache-2.0
base_model: hemlang/Hemlock2-Coder-7B
datasets:
  - hemlang/hemlock-codex3-SFT
tags:
  - hemlock
  - code
  - grpo
  - reinforcement-learning

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.