Instructions to use TheBloke/DiscoLM_German_7b_v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/DiscoLM_German_7b_v1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/DiscoLM_German_7b_v1-GGUF", dtype="auto")

llama-cpp-python

How to use TheBloke/DiscoLM_German_7b_v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/DiscoLM_German_7b_v1-GGUF",
	filename="discolm_german_7b_v1.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TheBloke/DiscoLM_German_7b_v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/DiscoLM_German_7b_v1-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 TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/DiscoLM_German_7b_v1-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 TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheBloke/DiscoLM_German_7b_v1-GGUF with Ollama:
```
ollama run hf.co/TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheBloke/DiscoLM_German_7b_v1-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 TheBloke/DiscoLM_German_7b_v1-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 TheBloke/DiscoLM_German_7b_v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheBloke/DiscoLM_German_7b_v1-GGUF to start chatting

Docker Model Runner
How to use TheBloke/DiscoLM_German_7b_v1-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/DiscoLM_German_7b_v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/DiscoLM_German_7b_v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DiscoLM_German_7b_v1-GGUF-Q4_K_M

List all available models

lemonade list

Endless Spaces

by vacanickel - opened Jan 20, 2024

Discussion

vacanickel

Jan 20, 2024

Used it with ollama, did the right template, it does generate endless spaces and lines after an answer and doesn't stop

Blizado

Jan 21, 2024

Yes. Didn't happen with the original model, but with the GGUF (I used KoboldCCP) version. Didn't tested GPTQ and AWQ.

jphme

Jan 24, 2024

Our bad, we had a config issue that caused this. Was fixed in the meantime (and I verified that gguf quants are fine now), see here : https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1/commit/560f972f9f735fc9289584b3aa8d75d0e539c44e .

Already pinged @TheBloke and asked if he can redo affected quants - huge sorry for this oversight on our side!

jplenio

Jan 26, 2024

Works now like a charm! :) Thanks for the fix!

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