Instructions to use KnutJaegersberg/2-bit-LLMs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/2-bit-LLMs with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="KnutJaegersberg/2-bit-LLMs",
	filename="WizardLM-70b-gguf-xs.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 KnutJaegersberg/2-bit-LLMs 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 KnutJaegersberg/2-bit-LLMs
# Run inference directly in the terminal:
llama cli -hf KnutJaegersberg/2-bit-LLMs

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KnutJaegersberg/2-bit-LLMs
# Run inference directly in the terminal:
llama cli -hf KnutJaegersberg/2-bit-LLMs

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 KnutJaegersberg/2-bit-LLMs
# Run inference directly in the terminal:
./llama-cli -hf KnutJaegersberg/2-bit-LLMs

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 KnutJaegersberg/2-bit-LLMs
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KnutJaegersberg/2-bit-LLMs

Use Docker

docker model run hf.co/KnutJaegersberg/2-bit-LLMs

LM Studio
Jan

vLLM

How to use KnutJaegersberg/2-bit-LLMs with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/2-bit-LLMs"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/2-bit-LLMs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/2-bit-LLMs

Ollama
How to use KnutJaegersberg/2-bit-LLMs with Ollama:
```
ollama run hf.co/KnutJaegersberg/2-bit-LLMs
```

Unsloth Studio

How to use KnutJaegersberg/2-bit-LLMs 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 KnutJaegersberg/2-bit-LLMs 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 KnutJaegersberg/2-bit-LLMs to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KnutJaegersberg/2-bit-LLMs to start chatting

Atomic Chat new
Docker Model Runner
How to use KnutJaegersberg/2-bit-LLMs with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/2-bit-LLMs
```

Lemonade

How to use KnutJaegersberg/2-bit-LLMs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KnutJaegersberg/2-bit-LLMs

Run and chat with the model

lemonade run user.2-bit-LLMs-{{QUANT_TAG}}

List all available models

lemonade list

Word of thanks and suggestions for more 120B models

by D8A - opened Feb 16, 2024

Discussion

D8A

Feb 16, 2024

Hello there!

I recently found your collection and I love it! Thanks for all your great work.

Might I ask if you can consider adding the new IQ 2-bit XS quants for Goliath-120B and Tess-XL-v1.0-120B. These models seem to be even better from both benchmarks and anecdotal evidence posted by others. 120B is also more resistant to the loss of 2-Bit quants. Thanks in advance and keep up the good work :)

KnutJaegersberg

Owner Feb 16, 2024

I wasn't planning to make a lot of more models. Currently trying to upload a miqu 120b model. I also want to do bigweave. but that's pretty much it. there are now also others doing this kind of quantizations :)

KnutJaegersberg changed discussion status to closed Feb 16, 2024

D8A

Feb 16, 2024

I wasn't planning to make a lot of more models. Currently trying to upload a miqu 120b model. I also want to do bigweave. but that's pretty much it. there are now also others doing this kind of quantizations :)

Okay that's fine. Do you use local or cloud to create these quants? and can you still tell me how (on what) you generated the imatrix files? :)

KnutJaegersberg

Owner Feb 18, 2024

local workstation, on cpu only, i9 but already 3 years old. I don't think ram requirements are high, though. with 100 chunks, making an imatrix on the 20k random words dataset takes 10 hours up to a day, depending on model size. quantization takes 1-2 hours.

KnutJaegersberg

Owner Feb 18, 2024

I simply took the file 20k_random_data.txt from this discussion

https://github.com/ggerganov/llama.cpp/discussions/5006

D8A

Feb 18, 2024

appreciated! thanks

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