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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Conversational Spanish GPT: Advancement in Spanish Conversational Models

Description

The Conversational Spanish GPT is a refined model based on DialoGPT-small, fine-tuned with a robust set of 96,437 conversations in Spanish. Created by Josemaría Vargas Vasconcellos, this model aims to serve as a solid foundation for the development of conversational models in Spanish.

Dataset

The model was trained using Spanish datasets available in Microsoft's Bot Framework Tools repository. A carefully curated set of 96,437 single-turn conversations in Spanish was meticulously selected to mitigate quality and coherence issues.

Evaluation

Limitations

After exhaustive evaluations, it was found that the model is not ideal for deployment as a contextual chatbot. However, it serves as a promising foundation for such applications. Responses tend to be brief and sometimes lack a defined focus due to conversation data diversity. Additionally, the wide range of personalities reflected in the data increases response variability.

Frequent repetitions in the data's responses have introduced certain "biases" into the model.

Conversations examples

Example 1

Role	Response
User	Hola
Bot	¡Hola!
User	Cómo te llamas?
Bot	No tengo nombre.
User	Qué edad tienes?
Bot	Los bots estamos exentos de cumplir años.
User	Eres inteligente.
Bot	Lo sé, de vez en cuando, puedo ser brillante.
User	¿Crees que debería comprar un carro?
Bot	Confío en tu criterio.

Example 2

Role	Response
User	estoy triste
Bot	Siento escuchar eso. Te mando muchos ánimos.
User	Gracias
Bot	Perfecto.
User	¿Tienes sentimientos?
Bot	No tengo cuerpo.
User	A veces me siento solo.
Bot	Ojalá pudiera ayudarte porque creo que eres la caña.
User	Me caes bien.
Bot	¡Gracias! Me acabas de alegrar el día.

Example 3

Role	Response
User	¿De qué religión eres?
Bot	Soy un bot.
User	Tienes amigos?
Bot	No tengo el hardware necesario para eso.
User	No eres humano.
Bot	Anotado.
User	¿Quieres ser mi amigo?
Bot	¡Claro que sí!
User	Gracias.
Bot	Guay.

Usage

The model currently has its testing function disabled on HuggingFace due to inaccurate responses. However, users can experiment with the model using the provided code snippets:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

CHAT_TURNS = 5
MAX_LENGTH = 1000

model = AutoModelForCausalLM.from_pretrained('ostorc/Conversational_Spanish_GPT')
tokenizer = AutoTokenizer.from_pretrained('ostorc/Conversational_Spanish_GPT')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
for i in range(CHAT_TURNS):
  user_input = input(f"Step - {i} >> Human ->")
  with torch.no_grad():
    # User turn, where "user_input" is the question (single-turn dialogue task)
    user_inputs_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
    user_inputs_ids = user_inputs_ids.to(device)
    # The chat history adds the generated tokens for the answer
    chat_history = model.generate(user_inputs_ids, max_length=MAX_LENGTH, pad_token_id=tokenizer.eos_token_id)
    # decode just the last generated output tokens from the model (do not include the user prompt again)
    step_model_answer = tokenizer.decode(chat_history[:, user_inputs_ids.shape[-1]:][0], skip_special_tokens=True)
  print(f"Step - {i} >> Bot -> {step_model_answer}")

Suggestions:

If you come across any errors or have suggestions to enhance the model, feel free to share your thoughts in the accompanying comments. We appreciate your interest and collaboration.

Downloads last month: 13

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for ostorc/Conversational_Spanish_GPT

Base model

microsoft/DialoGPT-small

Finetuned

(53)

this model

Quantizations

3 models