Instructions to use Undi95/Mistral-7B-claude-chat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Undi95/Mistral-7B-claude-chat-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Undi95/Mistral-7B-claude-chat-GGUF", filename="Mistral-7B-claude-chat.q4_k_s.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/Mistral-7B-claude-chat-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S # Run inference directly in the terminal: llama-cli -hf Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S # Run inference directly in the terminal: llama-cli -hf Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
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/Mistral-7B-claude-chat-GGUF:Q4_K_S # Run inference directly in the terminal: ./llama-cli -hf Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
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/Mistral-7B-claude-chat-GGUF:Q4_K_S # Run inference directly in the terminal: ./build/bin/llama-cli -hf Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
Use Docker
docker model run hf.co/Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
- LM Studio
- Jan
- Ollama
How to use Undi95/Mistral-7B-claude-chat-GGUF with Ollama:
ollama run hf.co/Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
- Unsloth Studio
How to use Undi95/Mistral-7B-claude-chat-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/Mistral-7B-claude-chat-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/Mistral-7B-claude-chat-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/Mistral-7B-claude-chat-GGUF to start chatting
- Docker Model Runner
How to use Undi95/Mistral-7B-claude-chat-GGUF with Docker Model Runner:
docker model run hf.co/Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
- Lemonade
How to use Undi95/Mistral-7B-claude-chat-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Undi95/Mistral-7B-claude-chat-GGUF:Q4_K_S
Run and chat with the model
lemonade run user.Mistral-7B-claude-chat-GGUF-Q4_K_S
List all available models
lemonade list
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Description
This repo contains quantized files of Mistral-7B-claude-chat.
Quantization of Norquinal/Mistral-7B-claude-chat
All credit go to Norquinal
datasets: - Norquinal/claude_multiround_chat_1k
This is the Mistral-7B-v0.1 model fine-tuned using QLoRA (4-bit precision) on my claude_multiround_chat_1k dataset, which is a randomized subset of ~1000 samples from my claude_multiround_chat_30k dataset.
Do not take this model very seriously, it is probably not very good. I haven't a clue of what I'm doing. I just thought it was a fun thing to make.
Prompt Format
The model was finetuned with the Vicuna 1.1 prompt format:
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: {instruction}
ASSISTANT:
Use in Text Generation Web UI
Install the bleeding-edge version of transformers from source:
pip install git+https://github.com/huggingface/transformers
Or, alternatively, change model_type in config.json from mistral to llama.
Example Usage
USER: First, give a brief overview of Chinese cuisine, including its regional diversity. next, describe the importance of the five flavors in Chinese cooking. Then, mention three popular Chinese dishes and their main ingredients. After that, provide a popular Chinese cooking technique and an example of a dish prepared using that technique. Finally, discuss the role of tea in traditional Chinese culture.
ASSISTANT: Chinese cuisine is incredibly diverse due to its large geographic area with different climates and resources available. Regional specialties include Sichuan spicy hot pot, Cantonese dim sum and seafood dishes, Beijing roast duck, and Hunan stir-fries.
The five basic tastes that guide Chinese cookery are sweetness, sourness, bitterness, saltiness, and pungency (spiciness). These contrasting flavors are used together to create balance in each dish.
Some classic Chinese dishes include dumplings filled with meat or vegetables, spring rolls stuffed with vegetables and meat wrapped in thin pastry, and noodles served in soups or stir fried with sauces and vegetables.
A common Chinese cooking technique is braising, where food is slowly cooked in a small amount of liquid until tender and flavorful. An example would be beef brisket braised in soy sauce, ginger and star anise for hours until falling apart.
Tea plays a central role in Chinese culture as it represents hospitality, relaxation and socializing. Green teas are most commonly consumed but black, oolong and white varieties also exist. Tea drinking rituals involve preparing and serving tea in specific ways depending on context and occasion.
In summary, Chinese cuisine offers a rich culinary tradition influenced by regional differences, an emphasis on balancing the five basic flavors, and a focus on simple yet flavorful preparations using fresh seasonal produce and high quality meats. Tea acts as both a refreshment and symbol of cultural refinement within Chinese society. I hope this overview provides an interesting starting point for further exploration into the fascinating world of Chinese gastronomy!
If you want to support me, you can here.
- Downloads last month
- 331
4-bit
5-bit
6-bit
8-bit