Instructions to use rdubwiley/agenda-parser-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rdubwiley/agenda-parser-medium with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rdubwiley/agenda-parser-medium",
	filename="agenda-parser-medium-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use rdubwiley/agenda-parser-medium 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 rdubwiley/agenda-parser-medium:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rdubwiley/agenda-parser-medium:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rdubwiley/agenda-parser-medium:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rdubwiley/agenda-parser-medium:Q4_K_M

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 rdubwiley/agenda-parser-medium:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rdubwiley/agenda-parser-medium:Q4_K_M

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 rdubwiley/agenda-parser-medium:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rdubwiley/agenda-parser-medium:Q4_K_M

Use Docker

docker model run hf.co/rdubwiley/agenda-parser-medium:Q4_K_M

LM Studio
Jan

vLLM

How to use rdubwiley/agenda-parser-medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rdubwiley/agenda-parser-medium"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rdubwiley/agenda-parser-medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rdubwiley/agenda-parser-medium:Q4_K_M

Ollama
How to use rdubwiley/agenda-parser-medium with Ollama:
```
ollama run hf.co/rdubwiley/agenda-parser-medium:Q4_K_M
```

Unsloth Studio

How to use rdubwiley/agenda-parser-medium 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 rdubwiley/agenda-parser-medium 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 rdubwiley/agenda-parser-medium to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rdubwiley/agenda-parser-medium to start chatting

How to use rdubwiley/agenda-parser-medium with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdubwiley/agenda-parser-medium:Q4_K_M

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": "rdubwiley/agenda-parser-medium:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rdubwiley/agenda-parser-medium with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdubwiley/agenda-parser-medium:Q4_K_M

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 rdubwiley/agenda-parser-medium:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use rdubwiley/agenda-parser-medium with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdubwiley/agenda-parser-medium:Q4_K_M

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 "rdubwiley/agenda-parser-medium:Q4_K_M" \
  --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 rdubwiley/agenda-parser-medium with Docker Model Runner:
```
docker model run hf.co/rdubwiley/agenda-parser-medium:Q4_K_M
```

Lemonade

How to use rdubwiley/agenda-parser-medium with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rdubwiley/agenda-parser-medium:Q4_K_M

Run and chat with the model

lemonade run user.agenda-parser-medium-Q4_K_M

List all available models

lemonade list

rdubwiley commited on Jun 10

Commit

ffdb43e

verified ·

1 Parent(s): 0b97131

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -46,20 +46,20 @@ It reads the tool's result, then emits the next action, until it calls `final_an
 ## How it was trained
-1. **Teacher traces.** Two strong teacher models — **Kimi k2.6** and **DeepSeek 4 pro** (via [OpenCode Go](https://opencode.ai)) — drove the *real* agent loop over 7 public agenda packets and a set of local-government legal questions. Tools executed live, so every observation is grounded.
 2. **Judge filtering.** Each completed trace's final answer was scored for **faithfulness** against the text the agent actually retrieved (fast OpenCode-Go judge); only high-faithfulness traces were kept. One accepted agent step = one training example.
-3. **SFT.** LoRA on the base's attention projections (q/k/v/o), 3 epochs over **204 examples** (held-out packet excluded — see Evaluation), full-sequence loss (the Gemma chat template lacks `{% generation %}` markers for assistant-only loss), bf16 + gradient checkpointing, then **merged** and converted to GGUF.
 | hyperparameter | value |
 |---|---|
-| LoRA rank / α / dropout | 16 / 32 / 0.05 |
-| target modules | attention `q_proj,k_proj,v_proj,o_proj` (auto-detected real `nn.Linear`) |
-| epochs | 3 |
 | learning rate | 1e-4 (cosine, 3% warmup) |
 | batch × grad-accum | 1 × 16 |
 | max sequence length | 4096 |
 | precision / GPU | bf16 / H100 |
-| final in-training token accuracy | ~0.74 |
 The full training/generation pipeline (trace capture, judge, LoRA, merge, GGUF) is reproducible from the dataset card.

 ## How it was trained
+1. **Teacher traces.** Two strong teacher models — **Kimi k2.6** and **DeepSeek 4 pro** (via [OpenCode Go](https://opencode.ai)) — drove the *real* agent loop over 11 public agenda packets and a set of local-government legal questions. Tools executed live, so every observation is grounded.
 2. **Judge filtering.** Each completed trace's final answer was scored for **faithfulness** against the text the agent actually retrieved (fast OpenCode-Go judge); only high-faithfulness traces were kept. One accepted agent step = one training example.
+3. **SFT.** LoRA on the base's attention projections (q/k/v/o), 4 epochs over **974 examples** (held-out packet excluded — see Evaluation), full-sequence loss (the Gemma chat template lacks `{% generation %}` markers for assistant-only loss), bf16 + gradient checkpointing, then **merged** and converted to GGUF.
 | hyperparameter | value |
 |---|---|
+| LoRA rank / α / dropout | 32 / 64 / 0.05 |
+| target modules | attention + MLP `q,k,v,o,gate,up,down_proj` (auto-detected real `nn.Linear`) |
+| epochs | 4 |
 | learning rate | 1e-4 (cosine, 3% warmup) |
 | batch × grad-accum | 1 × 16 |
 | max sequence length | 4096 |
 | precision / GPU | bf16 / H100 |
+| final in-training token accuracy | ~0.96 |
 The full training/generation pipeline (trace capture, judge, LoRA, merge, GGUF) is reproducible from the dataset card.