Instructions to use eugenehp/maya1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use eugenehp/maya1 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 eugenehp/maya1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eugenehp/maya1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf eugenehp/maya1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eugenehp/maya1: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 eugenehp/maya1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf eugenehp/maya1: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 eugenehp/maya1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf eugenehp/maya1:Q4_K_M

Use Docker

docker model run hf.co/eugenehp/maya1:Q4_K_M

LM Studio
Jan
Ollama
How to use eugenehp/maya1 with Ollama:
```
ollama run hf.co/eugenehp/maya1:Q4_K_M
```

Unsloth Studio

How to use eugenehp/maya1 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 eugenehp/maya1 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 eugenehp/maya1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for eugenehp/maya1 to start chatting

How to use eugenehp/maya1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf eugenehp/maya1: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": "eugenehp/maya1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use eugenehp/maya1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf eugenehp/maya1: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 "eugenehp/maya1: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 eugenehp/maya1 with Docker Model Runner:
```
docker model run hf.co/eugenehp/maya1:Q4_K_M
```

Lemonade

How to use eugenehp/maya1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eugenehp/maya1:Q4_K_M

Run and chat with the model

lemonade run user.maya1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use eugenehp/maya1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf eugenehp/maya1: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 eugenehp/maya1:Q4_K_M

Run Hermes

hermes

Atomic Chat

eugenehp commited on 22 days ago

Commit

717480c

verified ·

1 Parent(s): 69db56e

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +17 -10

README.md CHANGED Viewed

@@ -13,21 +13,28 @@ tags:
 Maya1 speech LM GGUF + tokenizer for RLX (needs SNAC separately).
-**Kind:** Staging redistrib of an upstream checkpoint for RLX runners.
-**Suggested Hub repo:** `eugenehp/maya1`
-**Upstream:** https://huggingface.co/mradermacher/maya1-GGUF
-**RLX crate:** [`rlx-maya1`](https://github.com/MIT-RLX/rlx-models/tree/main/crates/rlx-maya1)
-## Contents
-Weight tensors and configs in this directory (see file listing on the Hub).
 ## Run with RLX
-From [rlx-models](https://github.com/MIT-RLX/rlx-models) with this directory as the model path:
 ```bash
 cargo run -p rlx-maya1 --release -- --weights maya1.Q4_K_M.gguf
@@ -39,6 +46,6 @@ Apache License 2.0 — see `LICENSE`. Inherit upstream terms when redistributing
 Original weights and authorship: https://huggingface.co/mradermacher/maya1-GGUF
-## Staging note
-Prepared from the local `weights/` tree in [rlx-models](https://github.com/MIT-RLX/rlx-models) for a future standalone Hub upload. Prefer fetching upstream when this is only a redistrib.

 Maya1 speech LM GGUF + tokenizer for RLX (needs SNAC separately).
+| Field | Value |
+|---|---|
+| **Hub id** | [`eugenehp/maya1`](https://huggingface.co/eugenehp/maya1) |
+| **Kind** | Staging redistrib of an upstream checkpoint for RLX runners. |
+| **RLX crate** | [`rlx-maya1`](https://github.com/MIT-RLX/rlx-models/tree/main/crates/rlx-maya1) |
+| **Upstream** | https://huggingface.co/mradermacher/maya1-GGUF |
+## Quick start
+```bash
+hf download eugenehp/maya1 --local-dir .
+cargo run -p rlx-maya1 --release -- --weights maya1.Q4_K_M.gguf
+```
+## File highlights
+- `maya1.Q4_K_M.gguf` (1.9 GiB)
+- `tokenizer.json` (21.8 MiB)
 ## Run with RLX
+Clone [rlx-models](https://github.com/MIT-RLX/rlx-models), place this repo under `weights/tts/maya1` (or pass the path explicitly), then:
 ```bash
 cargo run -p rlx-maya1 --release -- --weights maya1.Q4_K_M.gguf
 Original weights and authorship: https://huggingface.co/mradermacher/maya1-GGUF
+## Redistrib note
+This Hub repo exists so RLX recipes have a stable fetch target. When you only need the upstream checkpoint, prefer the Upstream link above.