Edit model card

internlm-chatbode-7b

ChatBode Logo

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.

Características Principais

  • Modelo Base: internlm/internlm2-chat-7b
  • Dataset para Fine-tuning: UltraAlpaca
  • Treinamento: O treinamento foi realizado a partir do fine-tuning, usando QLoRA, do internlm2-chat-7b.

Exemplo de uso

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/internlm-chatbode-7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("recogna-nlp/internlm-chatbode-7b", 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/internlm-chatbode-7b"
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)

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric Value
Average 69.54
ENEM Challenge (No Images) 63.05
BLUEX (No Images) 51.46
OAB Exams 42.32
Assin2 RTE 91.33
Assin2 STS 80.69
FaQuAD NLI 79.80
HateBR Binary 87.99
PT Hate Speech Binary 68.09
tweetSentBR 61.11
Downloads last month
74
Safetensors
Model size
7.74B params
Tensor type
FP16
·
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.

Model tree for recogna-nlp/internlm-chatbode-7b

Adapters
4 models

Space using recogna-nlp/internlm-chatbode-7b 1

Evaluation results