Instructions to use TOAQ/Leon-7B-Research-Radio-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TOAQ/Leon-7B-Research-Radio-v1 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TOAQ/Leon-7B-Research-Radio-v1", dtype="auto")

llama-cpp-python

How to use TOAQ/Leon-7B-Research-Radio-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TOAQ/Leon-7B-Research-Radio-v1",
	filename="leon-v0.0.1-mistral-7b-instruct-v0.3.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TOAQ/Leon-7B-Research-Radio-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TOAQ/Leon-7B-Research-Radio-v1: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 TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TOAQ/Leon-7B-Research-Radio-v1: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 TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M

Use Docker

docker model run hf.co/TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M

LM Studio
Jan
Ollama
How to use TOAQ/Leon-7B-Research-Radio-v1 with Ollama:
```
ollama run hf.co/TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M
```

Unsloth Studio new

How to use TOAQ/Leon-7B-Research-Radio-v1 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 TOAQ/Leon-7B-Research-Radio-v1 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 TOAQ/Leon-7B-Research-Radio-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TOAQ/Leon-7B-Research-Radio-v1 to start chatting

Pi new

How to use TOAQ/Leon-7B-Research-Radio-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TOAQ/Leon-7B-Research-Radio-v1: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": "TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TOAQ/Leon-7B-Research-Radio-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TOAQ/Leon-7B-Research-Radio-v1: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 TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use TOAQ/Leon-7B-Research-Radio-v1 with Docker Model Runner:
```
docker model run hf.co/TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M
```

Lemonade

How to use TOAQ/Leon-7B-Research-Radio-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TOAQ/Leon-7B-Research-Radio-v1:Q4_K_M

Run and chat with the model

lemonade run user.Leon-7B-Research-Radio-v1-Q4_K_M

List all available models

lemonade list

🎙️ Léon-v1 : Podcast Research Assistant

📄 Read the full Technical Report on TOAQ

Léon is a fine-tuned model based on Mistral 7B v0.3, optimised to transform complex research documents (LaTeX/PDF) into immersive and accessible podcast scripts.

This v1 version introduces the concept of Temporal Positioning, allowing the generation of structured scripts without redundancies when concatenating long segments.

🚀 Technical Specifications

Base model: Mistral 7B v0.3 (Unsloth optimised)
Training method: QLoRA (4-bit quantisation)
Infrastructure: NVIDIA A100 (40GB VRAM)
Dataset: 450 pairs of instructions distilled from 41 scientific documents.
Output format: Plain text with SSML tags <break time="Xs" />.

🛠️ Training Hyperparameters

Parameter	Value
Learning Rate	1e-4
Global Batch Size	16 (4x4)
Steps	150
Epochs	6
Optimizer	AdamW 8-bit
Precision	Bfloat16 (Native A100 support)

📊 Performance (Convergence)

The training showed very stable convergence, going from an initial loss of 2.43 to a final loss of 1.06, with an overall minimum of 0.93 (step 149).

Training Runtime: 455.59 seconds
Throughput: 5.26 samples/second
VRAM Peak: 7.6 GB

🎭 Usage (Prompt Engineering)

Léon-v1 uses position tags to structure the narrative:

Introduction (Hook + Presentation)

[Position: START]
Document : [Insert LaTeX text here]

Body of the subject (Technique & Popularisation)

[Position: MIDDLE]
Context : [Summary of the previous segment]
Document : [Next data block]

Conclusion (Outro & Signature)

[Position: END]

⚠️ Limitations & Ethics

Léon is designed for popular science. Although powerful, it can sometimes oversimplify complex mathematical concepts. Always check the output against the source document.

📝 Citation

If you use this template for your research or podcast projects:

@misc{toaq_2026,
    author       = { TOAQ and Côme Bruneteau },
    title        = { Leon-7B-Research-Radio-v1 (Revision 70dbad6) },
    year         = 2026,
    url          = { https://huggingface.co/TOAQ/Leon-7B-Research-Radio-v1 },
    doi          = { 10.57967/hf/7866 },
    publisher    = { Hugging Face }
}

Downloads last month: 77

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TOAQ/Leon-7B-Research-Radio-v1

Base model

mistralai/Mistral-7B-v0.3

Quantized

unsloth/mistral-7b-v0.3-bnb-4bit

Quantized

(193)

this model