🚀 internlm-chatbode-7b

InternLm-ChatBode 是一个针对葡萄牙语进行微调的语言模型，它基于 InternLM2 模型开发。该模型通过使用 UltraAlpaca 数据集进行微调得到进一步优化。

✨ 主要特性

• 基础模型：internlm/internlm2-chat-7b
• 微调数据集：UltraAlpaca
• 训练方式：使用 QLoRA 对 internlm2-chat-7b 进行微调训练。

💻 使用示例

基础用法

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)

高级用法

可以使用 stream_chat 方法以流式方式生成回复：

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)

📚 详细文档

Open Portuguese LLM Leaderboard 评估结果

详细结果可在 此处 和 Open Portuguese LLM Leaderboard 上查看。

📄 引用

如果您想在研究中使用 Chatbode，请按以下方式引用：

@misc {chatbode_2024,
	author       = { Gabriel Lino Garcia, Pedro Henrique Paiola and  and João Paulo Papa},
	title        = { Chatbode },
	year         = {2024},
	url          = { https://huggingface.co/recogna-nlp/internlm-chatbode-7b/ },
	doi          = { 10.57967/hf/3317 },
	publisher    = { Hugging Face }
}