Undi95
/

Dawn-v2-70B-GGUF

GGUF

Not-For-All-Audiences

nsfw

Model card Files Files and versions

xet

Community

Instructions to use Undi95/Dawn-v2-70B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

llama-cpp-python

How to use Undi95/Dawn-v2-70B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Undi95/Dawn-v2-70B-GGUF",
	filename="Dawn-v2-70B.q2_k.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Undi95/Dawn-v2-70B-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 Undi95/Dawn-v2-70B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf Undi95/Dawn-v2-70B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Undi95/Dawn-v2-70B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf Undi95/Dawn-v2-70B-GGUF:Q2_K

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 Undi95/Dawn-v2-70B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf Undi95/Dawn-v2-70B-GGUF:Q2_K

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 Undi95/Dawn-v2-70B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Undi95/Dawn-v2-70B-GGUF:Q2_K

Use Docker

docker model run hf.co/Undi95/Dawn-v2-70B-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use Undi95/Dawn-v2-70B-GGUF with Ollama:
```
ollama run hf.co/Undi95/Dawn-v2-70B-GGUF:Q2_K
```

Unsloth Studio

How to use Undi95/Dawn-v2-70B-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 Undi95/Dawn-v2-70B-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 Undi95/Dawn-v2-70B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Undi95/Dawn-v2-70B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Undi95/Dawn-v2-70B-GGUF with Docker Model Runner:
```
docker model run hf.co/Undi95/Dawn-v2-70B-GGUF:Q2_K
```

Lemonade

How to use Undi95/Dawn-v2-70B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Undi95/Dawn-v2-70B-GGUF:Q2_K

Run and chat with the model

lemonade run user.Dawn-v2-70B-GGUF-Q2_K

List all available models

lemonade list

The biggest model merge yet?

by iandennismiller - opened Nov 7, 2023

Discussion

iandennismiller

Nov 7, 2023

This has to be one of the biggest merges I've ever seen. Congrats. You're pushing the envelope.

Did you run into any novel problems as you increased the number of models in the merge?

Undi95

Owner Nov 7, 2023

GGUF work fine, F16 work fine but I struggle to find how to make the exl2 work properly, output is now good on 2.4bpw
But I'm working on it, I used tools everyone use and I don't see why it wouldn't work on mine

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment