Instructions to use ncoop57/DiGPTame-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ncoop57/DiGPTame-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ncoop57/DiGPTame-medium") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ncoop57/DiGPTame-medium") model = AutoModelForCausalLM.from_pretrained("ncoop57/DiGPTame-medium") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ncoop57/DiGPTame-medium with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ncoop57/DiGPTame-medium" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ncoop57/DiGPTame-medium", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ncoop57/DiGPTame-medium
- SGLang
How to use ncoop57/DiGPTame-medium 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 "ncoop57/DiGPTame-medium" \ --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": "ncoop57/DiGPTame-medium", "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 "ncoop57/DiGPTame-medium" \ --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": "ncoop57/DiGPTame-medium", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ncoop57/DiGPTame-medium with Docker Model Runner:
docker model run hf.co/ncoop57/DiGPTame-medium
Finetuned DialoGPT model on Spanish Conversations
This model was finetuned from the original DialoGPT-medium model on subtitles from Spanish movies and telenovelas from the awesome OpenSubtitle dataset.
DialoGPT paper: https://arxiv.org/abs/1911.00536
Some example dialog from the model:
| Role | Response |
|---|---|
| User | ¿Cómo está el clima hoy? |
| Bot | Muy bien. |
| User | Eso es bueno escuchar. ¿Vas a ir a la playa? |
| Bot | No, también puedo regresar. |
| User | Oh bien, bueno, iré a la playa más tarde. |
| Bot | ¡No! |
| User | ¿Qué está mal con eso? |
| Bot | ¡Cómo que no! |
| User | Estoy confundido, ¿por qué no puedo ir a la playa? |
| Bot | ¡Cómo que no! |
| User | Explícamelo por favor. |
| Bot | ¡No! |
Using the model
Example code for trying out the model (taken directly from the DialoGPT-medium model card):
from transformers import AutoModelWithLMHead, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("ncoop57/DiGPTame-medium")
model = AutoModelWithLMHead.from_pretrained("ncoop57/DiGPTame-medium")
# Let's chat for 5 lines
for step in range(5):
# encode the new user input, add the eos_token and return a tensor in Pytorch
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
# append the new user input tokens to the chat history
bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
# generated a response while limiting the total chat history to 1000 tokens,
chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
# pretty print last ouput tokens from bot
print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
Training your own model
If you would like to finetune your own model or finetune this Spanish model, please checkout my blog post on that exact topic! https://nathancooper.io/i-am-a-nerd/chatbot/deep-learning/gpt2/2020/05/12/chatbot-part-1.html
- Downloads last month
- 7