Instructions to use fwizzer1/Fwizzer-R1-3B-EN-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use fwizzer1/Fwizzer-R1-3B-EN-v2 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 fwizzer1/Fwizzer-R1-3B-EN-v2
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-EN-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fwizzer1/Fwizzer-R1-3B-EN-v2
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-EN-v2

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 fwizzer1/Fwizzer-R1-3B-EN-v2
# Run inference directly in the terminal:
./llama-cli -hf fwizzer1/Fwizzer-R1-3B-EN-v2

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 fwizzer1/Fwizzer-R1-3B-EN-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fwizzer1/Fwizzer-R1-3B-EN-v2

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-EN-v2

LM Studio
Jan

vLLM

How to use fwizzer1/Fwizzer-R1-3B-EN-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fwizzer1/Fwizzer-R1-3B-EN-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fwizzer1/Fwizzer-R1-3B-EN-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-EN-v2

Ollama
How to use fwizzer1/Fwizzer-R1-3B-EN-v2 with Ollama:
```
ollama run hf.co/fwizzer1/Fwizzer-R1-3B-EN-v2
```
Unsloth Desktop
Docker Model Runner
How to use fwizzer1/Fwizzer-R1-3B-EN-v2 with Docker Model Runner:
```
docker model run hf.co/fwizzer1/Fwizzer-R1-3B-EN-v2
```

Lemonade

How to use fwizzer1/Fwizzer-R1-3B-EN-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fwizzer1/Fwizzer-R1-3B-EN-v2

Run and chat with the model

lemonade run user.Fwizzer-R1-3B-EN-v2-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Fwizzer-R1-3B-EN-v2 / Modelfile

fwizzer1

Add Ollama Modelfile with baked-in reasoning and system prompt

0b7aec4 verified about 1 month ago

Raw History Blame Contribute Delete

939 Bytes

	FROM ./Fwizzer-R1-3B-EN-Balanced.gguf

	TEMPLATE """{{ if .System }}[SYSTEM_PROMPT]{{ .System }}[/SYSTEM_PROMPT]{{ else }}[SYSTEM_PROMPT]You are Fwizzer-R1-3B, a helpful and reasoning language model. Always think step-by-step inside <think> and </think> tags before answering, then provide a clear, accurate, and concise response in the language of the user prompt.[/SYSTEM_PROMPT]{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}[INST]{{ .Content }}[/INST]{{ else if eq .Role "assistant" }}{{ .Content }}</s>{{ end }}{{ end }}"""

	SYSTEM """You are Fwizzer-R1-3B, a helpful and reasoning language model. Always think step-by-step inside <think> and </think> tags before answering, then provide a clear, accurate, and concise response in the language of the user prompt."""

	PARAMETER stop "</s>"
	PARAMETER stop "[INST]"
	PARAMETER stop "[/INST]"
	PARAMETER temperature 0.6
	PARAMETER top_p 0.95
	PARAMETER repeat_penalty 1.15