Instructions to use kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast")
model = AutoModelForCausalLM.from_pretrained("kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast

SGLang

How to use kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast with Docker Model Runner:
```
docker model run hf.co/kittn/Mixtral-8x7B-Instruct-v0.1-gpt-fast
```

Mixtral-8x7B (gpt-fast edition)

This repo holds quantized Mixtral-8x7B weights to be used in gpt-fast.

Compatibility

Conversion to int4 was broken, so this repo only holds fp8 weights. Practically speaking this means your GPU(s) need to be Ada Lovelace or newer, and have enough VRAM to hold the model + KV cache + activations.

I'm hoping it can work on a pair of 4090s, which combined have 48 GiB (51.539607552 GB) of VRAM. Ignoring all overhead, this leaves ~4.74 GB for KV-cache and activations, which should be enough (?).

TODO: Test on 2x4090 with TP=2

Notes

Conversion was done with (commit 7510a9d)

Downloads last month: 18