Instructions to use tktung/MultiSV_Mixtral-8x7B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tktung/MultiSV_Mixtral-8x7B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="tktung/MultiSV_Mixtral-8x7B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tktung/MultiSV_Mixtral-8x7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("tktung/MultiSV_Mixtral-8x7B-v0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tktung/MultiSV_Mixtral-8x7B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tktung/MultiSV_Mixtral-8x7B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tktung/MultiSV_Mixtral-8x7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tktung/MultiSV_Mixtral-8x7B-v0.1

SGLang

How to use tktung/MultiSV_Mixtral-8x7B-v0.1 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 "tktung/MultiSV_Mixtral-8x7B-v0.1" \
    --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": "tktung/MultiSV_Mixtral-8x7B-v0.1",
		"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 "tktung/MultiSV_Mixtral-8x7B-v0.1" \
        --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": "tktung/MultiSV_Mixtral-8x7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tktung/MultiSV_Mixtral-8x7B-v0.1 with Docker Model Runner:
```
docker model run hf.co/tktung/MultiSV_Mixtral-8x7B-v0.1
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Run the model

Instruction format

The template used to build a prompt for this Instruct model is defined as follows:

### USER:
{instruction1}
### RESPONSE:
{respone1}
### USER:
{instruction2}
### RESPONSE:
{respone2}

Run the model with the transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "tktung/MultiSV_Mixtral-8x7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,
                                             device_map="auto",
                                             dtype=torch.float16 # optional, load in 16-bit precision mode to reduce memory usage
                                            )
model.eval()

def make_prompt(instruction):
    return f"""### USER:
{instruction}
### RESPONSE:
"""

user_input = "Känner du till WARA M&L?"
input_prompt = make_prompt(user_input)
input_ids = tokenizer(input_prompt, return_tensors="pt")["input_ids"]
generated_token_ids = model.generate(
    inputs=input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.6,
    top_p=1,
)[0]
generated_text = tokenizer.decode(generated_token_ids)

Retrieval Augmented Generation

The model was trained with the following prompt format for RAG:

Vietnamese:

### USER:
Sử dụng ngữ cảnh sau để trả lời câu hỏi ở cuối:
{context}
Câu hỏi: {human_prompt}
### RESPONSE:

Swedish:

### USER:
Använd följande sammanhang för att svara på frågan:
{context}
Fråga: {human_prompt}
### RESPONSE:

Downloads last month: 14

Safetensors

Model size

47B params

Tensor type

BF16