Instructions to use ostorc/Conversational_Spanish_GPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ostorc/Conversational_Spanish_GPT with Transformers:

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

pipe = pipeline("text-generation", model="ostorc/Conversational_Spanish_GPT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ostorc/Conversational_Spanish_GPT")
model = AutoModelForCausalLM.from_pretrained("ostorc/Conversational_Spanish_GPT")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ostorc/Conversational_Spanish_GPT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ostorc/Conversational_Spanish_GPT

SGLang

How to use ostorc/Conversational_Spanish_GPT 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 "ostorc/Conversational_Spanish_GPT" \
    --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": "ostorc/Conversational_Spanish_GPT",
		"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 "ostorc/Conversational_Spanish_GPT" \
        --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": "ostorc/Conversational_Spanish_GPT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ostorc/Conversational_Spanish_GPT with Docker Model Runner:
```
docker model run hf.co/ostorc/Conversational_Spanish_GPT
```

Add default chat template to tokenizer_config.json

by Xenova HF Staff - opened Feb 16, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-2

Xenova

Feb 16, 2024

[Automated] This PR adds the default chat template to the tokenizer config, allowing the model to be used with the new conversational widget (see PR).

If the default is not appropriate for your model, please set tokenizer.chat_template to an appropriate template. See https://huggingface.co/docs/transformers/main/chat_templating for more information.

Add default chat template to tokenizer_config.json2c51097e

ostorc

Owner Feb 16, 2024

Hi Xenova,

Thank you very much for your Pull Request and for your interest in improving my model "Conversational_Spanish_GPT". I have carefully reviewed your suggestion to add a "chat_template" to the "tokenizer_config.json" file.

While I appreciate your time and effort, I would like to inform you that my model is single-turn, which means it is not trained to maintain conversational context. For this reason, the "chat_template" you propose would not be suitable. Using it could generate undesired or meaningless results, since the model does not have the ability to interpret conversation history.

I have considered alternatives such as not using a "chat_template" or creating a custom one for single-turn models. However, at this time, I believe the best option for my model is to not use a "chat_template".

I appreciate your understanding and cooperation. If you have any other suggestions or comments, please do not hesitate to let me know.

ostorc changed pull request status to closed Feb 16, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment