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

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
```

LlaMoE-Medium model image

Mixtral Experts with DeepSeek-MoE Architecture

Discord: https://discord.gg/cognitivecomputations

This is a direct extraction of the 8 experts from 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

To leverage instruction fine-tuning, your prompts should be enclosed with [INST] and [/INST] tokens. The very first instruction should begin with a begin-of-sentence id, while subsequent instructions should not. Assistant generation will conclude with an end-of-sentence token id.

Example

text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s>"
"[INST] Do you have mayonnaise recipes? [/INST]"

Applying the Chat Template

This format can be implemented using the apply_chat_template() method from the transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"  # the device to load the model onto

# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained("cognitivecomputations/DeepMixtral-8x7b-Instruct", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("cognitivecomputations/DeepMixtral-8x7b-Instruct")

# Define the conversation messages
messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

# Apply chat template
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)

# Generate response
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Special Thanks: Eric Hartford, and Fernando Neto.

Lucas Atkins (Crystalcareai)

Downloads last month: 13

Safetensors

Model size

47B params

Tensor type

BF16