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

Libraries

How to use cortexso/mixtral with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/mixtral",
	filename="model.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cortexso/mixtral with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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 cortexso/mixtral
# Run inference directly in the terminal:
./llama-cli -hf cortexso/mixtral

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 cortexso/mixtral
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/mixtral

Use Docker

docker model run hf.co/cortexso/mixtral

LM Studio
Jan
Ollama
How to use cortexso/mixtral with Ollama:
```
ollama run hf.co/cortexso/mixtral
```

Unsloth Studio new

How to use cortexso/mixtral 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 cortexso/mixtral 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 cortexso/mixtral to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use cortexso/mixtral with Docker Model Runner:
```
docker model run hf.co/cortexso/mixtral
```

Lemonade

How to use cortexso/mixtral with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/mixtral

Run and chat with the model

lemonade run user.mixtral-{{QUANT_TAG}}

List all available models

lemonade list

Pham commited on Jun 27, 2024

Commit

2ffcdb9

verified ·

1 Parent(s): 89c334b

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -4,20 +4,20 @@ license: apache-2.0
 ## Overview
-The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
 ## Variants
 | No | Variant | Cortex CLI command |
 | --- | --- | --- |
-| 1 | [8x7B-gguf](https://huggingface.co/cortexhub/llama3/tree/8B-gguf) | `cortex run mixtral:8x7B-gguf` |
 ## Use it with Jan (UI)
 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
 2. Use in Jan model Hub:
     ```
-    cortexhub/llama3
     ```
 ## Use it with Cortex (CLI)

 ## Overview
+The Mixtral-7x8B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-7x8Boutperforms Llama 2 70B on most benchmarks we tested.
 ## Variants
 | No | Variant | Cortex CLI command |
 | --- | --- | --- |
+| 1 | [7x8B-gguf](https://huggingface.co/cortexhub/mixtral/tree/7x8B-gguf) | `cortex run mixtral:7x8B-gguf` |
 ## Use it with Jan (UI)
 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
 2. Use in Jan model Hub:
     ```
+    cortexhub/mixtral
     ```
 ## Use it with Cortex (CLI)