体验链接

1. 🔗http://101.68.79.42:7861/

🚀更新

介绍

1. ✅ 对bloom-7b模型做了sft，本次版本为V2版本(使用了150w条有监督数据做sft)，相较于V1版本，效果更好！！！
2. 🚀 训练代码和推理代码全部分享，可以查看链接https://github.com/yuanzhoulvpi2017/zero_nlp/tree/main/chinese_bloom

如何使用

from transformers import AutoModelForCausalLM, AutoTokenizer


checkpoint = "yuanzhoulvpi/chinese_bloom_7b_chat_v2"#"bigscience/bloomz-3b" #"bigscience/bloom-7b1"# "output_dir/checkpoint-8260"#
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).half().cuda()

PROMPT_DICT = {
 "prompt_input": (
 "Below is an instruction that describes a task, paired with an input that provides further context. "
 "Write a response that appropriately completes the request.\n\n"
 "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
 ),
 "prompt_no_input": (
 "Below is an instruction that describes a task. "
 "Write a response that appropriately completes the request.\n\n"
 "### Instruction:\n{instruction}\n\n### Response:"
 ),
}

from typing import Optional
def generate_input(instruction:Optional[str]= None, input_str:Optional[str] = None) -> str:
 if input_str is None:
 return PROMPT_DICT['prompt_no_input'].format_map({'instruction':instruction})
 else:
 return PROMPT_DICT['prompt_input'].format_map({'instruction':instruction, 'input':input_str})


for i in range(5):
 print("*"*80)

 inputs = tokenizer.encode(generate_input(instruction="你是谁"), return_tensors="pt")
 outputs = model.generate(inputs,num_beams=3,
 max_new_tokens=512,
 do_sample=False, 
 top_k=10,
 penalty_alpha=0.6,
 temperature=0.8,
 repetition_penalty=1.2)
 print(tokenizer.decode(outputs[0]))