Downloads · 30 days
15
0% of all-time downloads
recogna-nlp/internlm2-chat-1_8b-ultracabrita
internlm2-chat-1_8b-ultracabrita is a text generation model from recogna-nlp. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
<p align="center" <img src="https://huggingface.co/recogna-nlp/internlm-chatbode-7b/resolve/main/1add1e52-f428-4c7c-bab2-3c6958e029fa.jpeg" alt="ChatBode Logo" width="400" style="margin-left:'auto' margin-right:'auto'…
Downloads · 30 days
15
0% of all-time downloads
All-time downloads
3.7K
Public
Repo size
7.6 GB
Likes
0
Public
Click a slice to open those files.
.bin3.8 GB · 100%
From the Hugging Face model README
O InternLm-ChatBode é um modelo de linguagem ajustado para o idioma português, desenvolvido a partir do modelo InternLM2. Este modelo foi refinado através do processo de fine-tuning utilizando o dataset UltraAlpaca.
A seguir um exemplo de código de como carregar e utilizar o modelo:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("recogna-nlp/internlm2-chat-1_8b-ultracabrita", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("recogna-nlp/internlm2-chat-1_8b-ultracabrita", torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()
response, history = model.chat(tokenizer, "Olá", history=[])
print(response)
response, history = model.chat(tokenizer, "O que é o Teorema de Pitágoras? Me dê um exemplo", history=history)
print(response)
As respostas podem ser geradas via stream utilizando o método stream_chat:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "recogna-nlp/internlm2-chat-1_8b-ultracabrita"
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16, trust_remote_code=True).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = model.eval()
length = 0
for response, history in model.stream_chat(tokenizer, "Olá", history=[]):
print(response[length:], flush=True, end="")
length = len(response)