Instructions to use BEE-spoke-data/Mixtral-GQA-400m-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BEE-spoke-data/Mixtral-GQA-400m-v2 with Transformers:

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

pipe = pipeline("text-generation", model="BEE-spoke-data/Mixtral-GQA-400m-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/Mixtral-GQA-400m-v2")
model = AutoModelForCausalLM.from_pretrained("BEE-spoke-data/Mixtral-GQA-400m-v2")
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 BEE-spoke-data/Mixtral-GQA-400m-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BEE-spoke-data/Mixtral-GQA-400m-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BEE-spoke-data/Mixtral-GQA-400m-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BEE-spoke-data/Mixtral-GQA-400m-v2

SGLang

How to use BEE-spoke-data/Mixtral-GQA-400m-v2 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 "BEE-spoke-data/Mixtral-GQA-400m-v2" \
    --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": "BEE-spoke-data/Mixtral-GQA-400m-v2",
		"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 "BEE-spoke-data/Mixtral-GQA-400m-v2" \
        --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": "BEE-spoke-data/Mixtral-GQA-400m-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BEE-spoke-data/Mixtral-GQA-400m-v2 with Docker Model Runner:
```
docker model run hf.co/BEE-spoke-data/Mixtral-GQA-400m-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BEE-spoke-data/Mixtral-GQA-400m-v2

testing code

# !pip install -U -q transformers datasets accelerate sentencepiece
import pprint as pp
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="BEE-spoke-data/Mixtral-GQA-400m-v2",
    device_map="auto",
)
pipe.model.config.pad_token_id = pipe.model.config.eos_token_id

prompt = "My favorite movie is Godfather because"

res = pipe(
    prompt,
    max_new_tokens=256,
    top_k=4,
    penalty_alpha=0.6,
    use_cache=True,
    no_repeat_ngram_size=4,
    repetition_penalty=1.1,
    renormalize_logits=True,
)
pp.pprint(res[0])

Downloads last month: 252

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for BEE-spoke-data/Mixtral-GQA-400m-v2

Quantizations

3 models