Instructions to use tensorblock/BioMistral-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/BioMistral-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/BioMistral-7B-GGUF",
	filename="BioMistral-7B-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tensorblock/BioMistral-7B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/BioMistral-7B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/BioMistral-7B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/BioMistral-7B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/BioMistral-7B-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 tensorblock/BioMistral-7B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/BioMistral-7B-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 tensorblock/BioMistral-7B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/BioMistral-7B-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/BioMistral-7B-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/BioMistral-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/BioMistral-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/BioMistral-7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/BioMistral-7B-GGUF:Q2_K

Ollama
How to use tensorblock/BioMistral-7B-GGUF with Ollama:
```
ollama run hf.co/tensorblock/BioMistral-7B-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/BioMistral-7B-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 tensorblock/BioMistral-7B-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 tensorblock/BioMistral-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/BioMistral-7B-GGUF to start chatting

Docker Model Runner
How to use tensorblock/BioMistral-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/BioMistral-7B-GGUF:Q2_K
```

Lemonade

How to use tensorblock/BioMistral-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/BioMistral-7B-GGUF:Q2_K

Run and chat with the model

lemonade run user.BioMistral-7B-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e373fb613ea2f511d19813ddc7054cd92d33ca8c83ac101a8572a12eb7537c5f
-size 3822025312

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5fc597ad078a991db4c264e0954f971fb1d3b2e9e368575bc8bd2152c6d2963d
-size 3164568160

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2696296ae76dd69189094cd45533113829de6a4a9006defd53e1a89bf400e4e
-size 4108917344

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2677df8c52793cd270b45e765d75d042092cae39ffdaa23cf54f8451dd102376
-size 4368439904

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:405926d5aadc1c70b8eb87c91feb2815cd4ce6856869f53c290ba9470850739e
-size 4140374624

tensorblock
/

BioMistral-7B-GGUF

Keep Q2_K/Q3_K_M gguf only