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
```

What specific dataset did you use?

by Alicorn-Max - opened Oct 23, 2024

Discussion

Alicorn-Max

Oct 23, 2024

Hi, I was curious about the specific dataset used for this. I would like to train a model like this, but with a newer dataset. Thanks!

ostorc

Owner Oct 30, 2024

Hello, Max!

The datasets I used to train the Conversational_Spanish_GPT model are available in the Microsoft Bot Framework Tools repository. In this repository, you’ll find numerous high-quality datasets in various languages, including one that I used:
https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/spanish/qna_chitchat_professional.tsv

However, I can’t point to just one dataset since I relied on several of them for training. Additionally, to adapt them to fine-tuning requirements, it was necessary to edit, convert, clean, and modify the files, which was a challenging process but definitely worth it.

I encourage you to train your own model, and I appreciate your interest in mine. Good luck!

ostorc changed discussion status to closed Nov 12, 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