Instructions to use emil2000/dialogpt-for-french-language with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emil2000/dialogpt-for-french-language with Transformers:

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

pipe = pipeline("text-generation", model="emil2000/dialogpt-for-french-language")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("emil2000/dialogpt-for-french-language")
model = AutoModelForCausalLM.from_pretrained("emil2000/dialogpt-for-french-language", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use emil2000/dialogpt-for-french-language with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emil2000/dialogpt-for-french-language"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emil2000/dialogpt-for-french-language",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/emil2000/dialogpt-for-french-language

SGLang

How to use emil2000/dialogpt-for-french-language 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 "emil2000/dialogpt-for-french-language" \
    --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": "emil2000/dialogpt-for-french-language",
		"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 "emil2000/dialogpt-for-french-language" \
        --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": "emil2000/dialogpt-for-french-language",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use emil2000/dialogpt-for-french-language with Docker Model Runner:
```
docker model run hf.co/emil2000/dialogpt-for-french-language
```

YAML Metadata Error:"tags[0]" must be a string

YAML Metadata Error:"tags[1]" must be a string

This model aims at being a french conversational agent. This consists of a fine-tuning of Dialo-GPT for french language. The dataset used gathers 36k conversations extracted from books, movies, interviews and dialogues for learning french.

More details about the model can be found there

Downloads last month: 17