Instructions to use yujiepan/mixtral-8xtiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/mixtral-8xtiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/mixtral-8xtiny-random")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/mixtral-8xtiny-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/mixtral-8xtiny-random")
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

vLLM

How to use yujiepan/mixtral-8xtiny-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yujiepan/mixtral-8xtiny-random

SGLang

How to use yujiepan/mixtral-8xtiny-random 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 "yujiepan/mixtral-8xtiny-random" \
    --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": "yujiepan/mixtral-8xtiny-random",
		"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 "yujiepan/mixtral-8xtiny-random" \
        --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": "yujiepan/mixtral-8xtiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yujiepan/mixtral-8xtiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/mixtral-8xtiny-random
```

Librarian Bot: Add moe tag to model

by librarian-bot - opened Jan 8, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

librarian-bot

Jan 8, 2024

This pull request aims to enrich the metadata of your model by adding an moe (Mixture of Experts) tag in the YAML block of your model's README.md.

How did we find this information? We infered that this model is a moe model based on the following criteria:

The model's name contains the string moe.
The model indicates it uses a moe architecture
The model's base model is a moe model

Why add this? Enhancing your model's metadata in this way:

Boosts Discoverability - It becomes easier to find mixture of experts models on the Hub
Helping understand the ecosystem - It becomes easier to understand the ecosystem of mixture of experts models on the Hub and how they are used

This PR comes courtesy of Librarian Bot. If you have any feedback, queries, or need assistance, please don't hesitate to reach out to @davanstrien.

Librarian Bot: Add moe tag to model3d8faf40

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md

· Sign up or log in to comment