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

Libraries

How to use PixN/MY_FIRST_RL with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PixN/MY_FIRST_RL",
	filename="qwen3_4b_checkpoint100_Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use PixN/MY_FIRST_RL with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PixN/MY_FIRST_RL:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PixN/MY_FIRST_RL:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/PixN/MY_FIRST_RL:Q4_K_M

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

Unsloth Studio new

How to use PixN/MY_FIRST_RL 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 PixN/MY_FIRST_RL 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 PixN/MY_FIRST_RL to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use PixN/MY_FIRST_RL with Docker Model Runner:
```
docker model run hf.co/PixN/MY_FIRST_RL:Q4_K_M
```

Lemonade

How to use PixN/MY_FIRST_RL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PixN/MY_FIRST_RL:Q4_K_M

Run and chat with the model

lemonade run user.MY_FIRST_RL-Q4_K_M

List all available models

lemonade list

⚠️This model isn't just a quantized model of unsloth/Qwen3-4B-Base

冬休みの自由研究としてUnslothのGRPOを使ってトレーニングしたQwen3-4B-Baseモデル。数学推論に特化させた…つもりなだけで実際はあんまりうまく動作しない。

Downloads last month: 10

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for PixN/MY_FIRST_RL

Base model

Qwen/Qwen3-4B-Base

Finetuned

unsloth/Qwen3-4B-Base

Quantized

(12)

this model