Instructions to use jubba/silverhand_mistral7b_v0_1_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jubba/silverhand_mistral7b_v0_1_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jubba/silverhand_mistral7b_v0_1_GGUF",
	filename="silverhand_mistral7b-v0.1.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jubba/silverhand_mistral7b_v0_1_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

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 jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

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 jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

Use Docker

docker model run hf.co/jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

LM Studio
Jan

vLLM

How to use jubba/silverhand_mistral7b_v0_1_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jubba/silverhand_mistral7b_v0_1_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": "jubba/silverhand_mistral7b_v0_1_GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

Ollama
How to use jubba/silverhand_mistral7b_v0_1_GGUF with Ollama:
```
ollama run hf.co/jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0
```

Unsloth Studio

How to use jubba/silverhand_mistral7b_v0_1_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 jubba/silverhand_mistral7b_v0_1_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 jubba/silverhand_mistral7b_v0_1_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jubba/silverhand_mistral7b_v0_1_GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use jubba/silverhand_mistral7b_v0_1_GGUF with Docker Model Runner:
```
docker model run hf.co/jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0
```

Lemonade

How to use jubba/silverhand_mistral7b_v0_1_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jubba/silverhand_mistral7b_v0_1_GGUF:Q8_0

Run and chat with the model

lemonade run user.silverhand_mistral7b_v0_1_GGUF-Q8_0

List all available models

lemonade list

Description

Mistral-7b model finetuned using SFT to respond like Johhny Silverhand from the Cyberpunk universe (Mike Pondsmith, CD Project Red).

The model can be used with ollama or any other application that supports a .gguf model file.

The model is quantized to 8 bits using llama.cpp

Downloads last month: 2

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit

Model tree for jubba/silverhand_mistral7b_v0_1_GGUF

Base model

mistralai/Mistral-7B-Instruct-v0.2

Quantized

(103)

this model