Instructions to use cloudyu/Mixtral_7Bx5_MoE_30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cloudyu/Mixtral_7Bx5_MoE_30B with Transformers:

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

pipe = pipeline("text-generation", model="cloudyu/Mixtral_7Bx5_MoE_30B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cloudyu/Mixtral_7Bx5_MoE_30B")
model = AutoModelForCausalLM.from_pretrained("cloudyu/Mixtral_7Bx5_MoE_30B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cloudyu/Mixtral_7Bx5_MoE_30B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cloudyu/Mixtral_7Bx5_MoE_30B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudyu/Mixtral_7Bx5_MoE_30B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cloudyu/Mixtral_7Bx5_MoE_30B

SGLang

How to use cloudyu/Mixtral_7Bx5_MoE_30B 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 "cloudyu/Mixtral_7Bx5_MoE_30B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudyu/Mixtral_7Bx5_MoE_30B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cloudyu/Mixtral_7Bx5_MoE_30B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudyu/Mixtral_7Bx5_MoE_30B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cloudyu/Mixtral_7Bx5_MoE_30B with Docker Model Runner:
```
docker model run hf.co/cloudyu/Mixtral_7Bx5_MoE_30B
```

Differences of the model and training process

by ankits0052 - opened Jan 11, 2024

Discussion

ankits0052

Jan 11, 2024

Is this model trained on instruction tuned data? How is the model 30B parameters?

ankits0052 changed discussion title from Difference of the model to Differences of the model and training process Jan 11, 2024

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

Tap or paste here to upload images

· Sign up or log in to comment