Instructions to use SuNavar/Pygenesis_ResolveExpert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SuNavar/Pygenesis_ResolveExpert with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SuNavar/Pygenesis_ResolveExpert",
	filename="pygenesis-resolve-q4km.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 SuNavar/Pygenesis_ResolveExpert 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 SuNavar/Pygenesis_ResolveExpert
# Run inference directly in the terminal:
llama cli -hf SuNavar/Pygenesis_ResolveExpert

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SuNavar/Pygenesis_ResolveExpert
# Run inference directly in the terminal:
llama cli -hf SuNavar/Pygenesis_ResolveExpert

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 SuNavar/Pygenesis_ResolveExpert
# Run inference directly in the terminal:
./llama-cli -hf SuNavar/Pygenesis_ResolveExpert

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 SuNavar/Pygenesis_ResolveExpert
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SuNavar/Pygenesis_ResolveExpert

Use Docker

docker model run hf.co/SuNavar/Pygenesis_ResolveExpert

LM Studio
Jan

vLLM

How to use SuNavar/Pygenesis_ResolveExpert with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SuNavar/Pygenesis_ResolveExpert

Ollama
How to use SuNavar/Pygenesis_ResolveExpert with Ollama:
```
ollama run hf.co/SuNavar/Pygenesis_ResolveExpert
```

Unsloth Studio

How to use SuNavar/Pygenesis_ResolveExpert 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 SuNavar/Pygenesis_ResolveExpert 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 SuNavar/Pygenesis_ResolveExpert to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SuNavar/Pygenesis_ResolveExpert to start chatting

How to use SuNavar/Pygenesis_ResolveExpert with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SuNavar/Pygenesis_ResolveExpert

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": "SuNavar/Pygenesis_ResolveExpert"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SuNavar/Pygenesis_ResolveExpert with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SuNavar/Pygenesis_ResolveExpert

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 SuNavar/Pygenesis_ResolveExpert

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use SuNavar/Pygenesis_ResolveExpert with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SuNavar/Pygenesis_ResolveExpert

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 "SuNavar/Pygenesis_ResolveExpert" \
  --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 SuNavar/Pygenesis_ResolveExpert with Docker Model Runner:
```
docker model run hf.co/SuNavar/Pygenesis_ResolveExpert
```

Lemonade

How to use SuNavar/Pygenesis_ResolveExpert with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SuNavar/Pygenesis_ResolveExpert

Run and chat with the model

lemonade run user.Pygenesis_ResolveExpert-{{QUANT_TAG}}

List all available models

lemonade list

SuNavar commited on 8 days ago

Commit

fe008b4

verified ·

1 Parent(s): 862e14a

Update README.md

Browse files

# Pygenesis ResolveExpert

Pygenesis ResolveExpert is a task-oriented assistant model for **DaVinci Resolve** workflows (Edit, Color, Fusion, Fairlight, Deliver), packaged for local inference as GGUF.

## Model Overview

`pygenesis-resolve-q4km.gguf` is a quantized local-inference variant of a Resolve-focused fine-tuned model.

Main goals:
- Provide practical, step-by-step help for real editing and post-production tasks.
- Keep latency reasonable on desktop hardware.
- Run fully on-device with no cloud dependency.

## Studio vs Free: Context Behavior

The model is the same in both editions.
The key difference is **how runtime context is provided**.

### DaVinci Resolve Studio (Integrated Plugin)

In Studio, the Workflow Integration plugin can automatically read and pass context such as:
- Current Resolve page (`Media`, `Cut`, `Edit`, `Fusion`, `Color`, `Fairlight`, `Deliver`)
- Current project and timeline names
- Basic timeline metadata

This usually improves relevance because answers are grounded in the user’s current working state.

### DaVinci Resolve Free (Companion App)

Resolve Free does not support the Workflow Integration plugin, so usage is via **Pygenesis Companion** (external app).

In this mode, context is provided manually:
- User selects the active page
- User can optionally provide project/timeline names

The model quality is unchanged, but contextual precision depends on the information entered by the user.

## Practical Summary

- **Same model weights** in Studio and Free.
- **Studio**: automatic context -> more situational responses.
- **Free**: manual context -> still useful responses, with lower contextual precision when input context is incomplete.

## Recommended Use Cases

- Resolve workflow troubleshooting ("how do I do X in Color/Fusion/Edit?").
- Page-specific checklists ("what should I review here?").
- Export and performance best practices.
- Actionable next steps for practical post-production decisions.

## Limitations

- Not a replacement for official Blackmagic documentation.
- Advanced workflows may still require iterative clarification.
- In Free mode, missing manual context can reduce specificity.

## Prompting Tips

For best results, include:
- Current Resolve page.
- Clear goal ("match two shots", "export for YouTube 4K", etc.).
- Constraints (GPU, Resolve version, footage type, deadline).

Example:
> "I am on the Color page. I have two shots with different exposure and need a fast matching workflow without damaging skin tones."

## Installation & Usage

Pygenesis ResolveExpert is distributed as a **packaged installer**, not as a manual developer setup.

The installer handles:
- GPU detection and inference backend selection (CUDA, Vulkan, or CPU)
- Model download from this Hugging Face repository
- UI installation for your Resolve edition

After installation:

| Edition | How you use it |
|---------|----------------|
| **DaVinci Resolve Studio** | Open the integrated plugin from **Workspace → Workflow Integrations → Pygenesis Resolve Tutor** |
| **DaVinci Resolve Free** | Launch **Pygenesis Companion** (standalone app installed alongside the model) |

Inference runs locally on your machine. No account or API key is required beyond downloading the model through the installer.

## Intended Users

Editors, colorists, and technical users who want a local assistant tailored to DaVinci Resolve workflows.

## Acknowledgements

- Built for the Pygenesis ResolveExpert project.
- Resolve integration behavior follows Blackmagic’s Studio/Free plugin constraints.

Files changed (1) hide show

README.md +12 -1

README.md CHANGED Viewed

@@ -1,3 +1,14 @@
 ---
 license: apache-2.0
----

 ---
 license: apache-2.0
+language:
+- en
+- es
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+pipeline_tag: text-generation
+tags:
+- davinci-resolve
+- video-editing
+- local-inference
+- gguf
+---