internlm-chatbode-7b

ChatBode Logo

O InternLm-ChatBode รฉ um modelo de linguagem ajustado para o idioma portuguรชs, desenvolvido a partir do modelo InternLM2. Este modelo foi refinado atravรฉs do processo de fine-tuning utilizando o dataset UltraAlpaca.

Caracterรญsticas 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 cรณdigo 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, "Olรก", history=[])
print(response)
response, history = model.chat(tokenizer, "O que รฉ o Teorema de Pitรกgoras? Me dรช um exemplo", history=history)
print(response)

As respostas podem ser geradas via stream utilizando o mรฉtodo 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, "Olรก", 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 ๐Ÿš€ 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

Citaรงรฃo

Se vocรช deseja utilizar o Chatbode em sua pesquisa, cite-o da seguinte maneira:

@misc {chatbode_2024,
    author       = { Gabriel Lino Garcia, Pedro Henrique Paiola and  and Joรฃo Paulo Papa},
    title        = { Chatbode },
    year         = {2024},
    url          = { https://huggingface.co/recogna-nlp/internlm-chatbode-7b/ },
    doi          = { 10.57967/hf/3317 },
    publisher    = { Hugging Face }
}
Downloads last month
58
Safetensors
Model size
8B params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ 2 Ask for provider support

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

Adapters
4 models
Quantizations
2 models

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

Evaluation results