Instructions to use bofenghuang/vigogne-2-13b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bofenghuang/vigogne-2-13b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="bofenghuang/vigogne-2-13b-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bofenghuang/vigogne-2-13b-instruct")
model = AutoModelForCausalLM.from_pretrained("bofenghuang/vigogne-2-13b-instruct")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bofenghuang/vigogne-2-13b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bofenghuang/vigogne-2-13b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bofenghuang/vigogne-2-13b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bofenghuang/vigogne-2-13b-instruct

SGLang

How to use bofenghuang/vigogne-2-13b-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 "bofenghuang/vigogne-2-13b-instruct" \
    --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": "bofenghuang/vigogne-2-13b-instruct",
		"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 "bofenghuang/vigogne-2-13b-instruct" \
        --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": "bofenghuang/vigogne-2-13b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bofenghuang/vigogne-2-13b-instruct with Docker Model Runner:
```
docker model run hf.co/bofenghuang/vigogne-2-13b-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Vigogne

Vigogne-2-13B-Instruct: A Llama-2 based French instruction-following model

Vigogne-2-13B-Instruct is a model based on LLaMA-2-13B that has been fine-tuned to follow French instructions.

For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne

Usage and License Notices: Vigogne-2-13B-Instruct follows the same usage policy as Llama-2, which can be found here.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from vigogne.preprocess import generate_instruct_prompt

model_name_or_path = "bofenghuang/vigogne-2-13b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")

user_query = "Expliquez la différence entre DoS et phishing."
prompt = generate_instruct_prompt(user_query)
input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
input_length = input_ids.shape[1]

generated_outputs = model.generate(
    input_ids=input_ids,
    generation_config=GenerationConfig(
        temperature=0.1,
        do_sample=True,
        repetition_penalty=1.0,
        max_new_tokens=512,
    ),
    return_dict_in_generate=True,
)
generated_tokens = generated_outputs.sequences[0, input_length:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)

You can also infer this model by using the following Google Colab Notebook.

Example Outputs

todo

Limitations

Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.