Instructions to use QuixiAI/DeepMixtral-8x7b-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/DeepMixtral-8x7b-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/DeepMixtral-8x7b-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("QuixiAI/DeepMixtral-8x7b-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuixiAI/DeepMixtral-8x7b-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuixiAI/DeepMixtral-8x7b-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuixiAI/DeepMixtral-8x7b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuixiAI/DeepMixtral-8x7b-Instruct

SGLang

How to use QuixiAI/DeepMixtral-8x7b-Instruct 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 "QuixiAI/DeepMixtral-8x7b-Instruct" \
    --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": "QuixiAI/DeepMixtral-8x7b-Instruct",
		"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 "QuixiAI/DeepMixtral-8x7b-Instruct" \
        --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": "QuixiAI/DeepMixtral-8x7b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuixiAI/DeepMixtral-8x7b-Instruct with Docker Model Runner:
```
docker model run hf.co/QuixiAI/DeepMixtral-8x7b-Instruct
```

Crystalcareai commited on May 5, 2024

Commit

50d4f86

verified ·

1 Parent(s): d197773

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -8,11 +8,11 @@ language:
 ## Mixtral Experts with DeepSeek-MoE Architecture
-This is a direct extraction of the 8 experts from [Mixtral-8x7b-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1), and placing them into the DeepSeek-MoE Architecture.
 - **Expert Configuration:** It is 2 experts per token.
 - **Performance:** Performance is identical to instruct, if not a little better.
-- **Evaluations:** Evals will come, it is more malleable to training.
 - **Experimentation:** This is the first of a few MoE expert extraction and modification projects we're working on, more to come. Enjoy.
 ## Instruction Format

 ## Mixtral Experts with DeepSeek-MoE Architecture
+This is a direct extraction of the 8 experts from [Mixtral-8x7b-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1), and a transfer of them into the DeepSeek-MoE Architecture.
 - **Expert Configuration:** It is 2 experts per token.
 - **Performance:** Performance is identical to instruct, if not a little better.
+- **Evaluations:** Evals will come when compute clears up, it also appears more malleable to training.
 - **Experimentation:** This is the first of a few MoE expert extraction and modification projects we're working on, more to come. Enjoy.
 ## Instruction Format