Instructions to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nbeerbower/Hemlock-Apothecary-7B-GRPO-e3",
	filename="Hemlock-Apothecary-7B-GRPO-e3-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 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/Hemlock-Apothecary-7B-GRPO-e3:Q8_0
# Run inference directly in the terminal:
llama cli -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0
# Run inference directly in the terminal:
llama cli -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3: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/Hemlock-Apothecary-7B-GRPO-e3:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3: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/Hemlock-Apothecary-7B-GRPO-e3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0

Use Docker

docker model run hf.co/nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0

LM Studio
Jan
Ollama
How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 with Ollama:
```
ollama run hf.co/nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0
```

Unsloth Studio

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 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/Hemlock-Apothecary-7B-GRPO-e3 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/Hemlock-Apothecary-7B-GRPO-e3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 to start chatting

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3: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/Hemlock-Apothecary-7B-GRPO-e3:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 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/Hemlock-Apothecary-7B-GRPO-e3: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/Hemlock-Apothecary-7B-GRPO-e3:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nbeerbower/Hemlock-Apothecary-7B-GRPO-e3: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/Hemlock-Apothecary-7B-GRPO-e3: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/Hemlock-Apothecary-7B-GRPO-e3 with Docker Model Runner:
```
docker model run hf.co/nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0
```

Lemonade

How to use nbeerbower/Hemlock-Apothecary-7B-GRPO-e3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nbeerbower/Hemlock-Apothecary-7B-GRPO-e3:Q8_0

Run and chat with the model

lemonade run user.Hemlock-Apothecary-7B-GRPO-e3-Q8_0

List all available models

lemonade list

Hemlock-Apothecary-7B-GRPO-e3

A best-of-N specialist variant of hemlang/Hemlock-Apothecary-7B: the epoch-3 checkpoint of an execution-reward GRPO run (grimoire / hemlock-rl) on hemlang/hemlock-codex3-SFT.

Know the trade-off (hembench zero-shot, n=5):

	pass@1	pass@5
Hemlock-Apothecary-7B	60.5%	68.4%
Apothecary-GRPO-e3	52.6%	71.1%

Mid-training RL dispersed the policy: lower first-try reliability, but the highest any-shot solve rate of any Hemlock model measured to date. Use the base Apothecary for single-shot generation; use this model when sampling several candidates and verifying with the interpreter — e.g. hembot --retry — where solve-rate within k samples is what matters. Notable per-level: systems/concurrency L4 pass@1 4/7 → 5/7, debugging L6 pass@5 3/5 → 4/5.

GRPO with LoRA r=16, β=0.1 KL, G=8, dynamic sampling, 267 deduplicated verified prompts, constant lr, checkpoint at epoch 3 of 4 (the epoch-4 endpoint re-concentrates and loses the pass@5 advantage). Q8_0 GGUF included.