Instructions to use TeeZee/Reflection-Llama-3.1-70B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeZee/Reflection-Llama-3.1-70B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TeeZee/Reflection-Llama-3.1-70B-GGUF",
	filename="mattshumer_Reflection-Llama-3.1-70B-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 Settings

llama.cpp

How to use TeeZee/Reflection-Llama-3.1-70B-GGUF 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 TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TeeZee/Reflection-Llama-3.1-70B-GGUF: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 TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TeeZee/Reflection-Llama-3.1-70B-GGUF: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 TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TeeZee/Reflection-Llama-3.1-70B-GGUF with Ollama:
```
ollama run hf.co/TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M
```

Unsloth Studio

How to use TeeZee/Reflection-Llama-3.1-70B-GGUF 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 TeeZee/Reflection-Llama-3.1-70B-GGUF 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 TeeZee/Reflection-Llama-3.1-70B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TeeZee/Reflection-Llama-3.1-70B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TeeZee/Reflection-Llama-3.1-70B-GGUF with Docker Model Runner:
```
docker model run hf.co/TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M
```

Lemonade

How to use TeeZee/Reflection-Llama-3.1-70B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TeeZee/Reflection-Llama-3.1-70B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Reflection-Llama-3.1-70B-GGUF-Q4_K_M

List all available models

lemonade list

Q4_K_M GGUF quant of Reflection-Llama-3.1-70B - fixed version.
Runs great on 48GB VRAM, tested.
Ollama modelfile added - version with original system prompt - output is split into "thinking" and "output" tags.
If you want llama 3.1 'vanilla' experience, just remove SYSTEM from modelfile before creating ollama model.

All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:

Downloads last month: 14

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Collection including TeeZee/Reflection-Llama-3.1-70B-GGUF

48 GB VRAM

Collection

Quants that run fast on 2x3090 consuming 48GB total VRAM. • 2 items • Updated Sep 9, 2024