metadata
license: openrail
datasets:
- LinkSoul/instruction_merge_set
language:
- zh
- en
widget:
- text: >-
[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as
helpfully as possible, while being safe. Your answers should not include
any harmful, unethical, racist, sexist, toxic, dangerous, or illegal
content. Please ensure that your responses are socially unbiased and
positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
用中文回答，When is the best time to visit Beijing, and do you have any
suggestions for me? [/INST]
example_title: 北京
- text: >-
[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as
helpfully as possible, while being safe. Your answers should not include
any harmful, unethical, racist, sexist, toxic, dangerous, or illegal
content. Please ensure that your responses are socially unbiased and
positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
用英文回答，特朗普是谁？ [/INST]
example_title: 特朗普是谁
Chinese Llama 2 7B
全部开源，完全可商用的中文版 Llama2 模型及中英文 SFT 数据集，输入格式严格遵循llama-2-chat的输入格式，以方便应用所有针对llama-2-chat的优化。
在线试玩
Talk is cheap, Show you the Demo.
快速测试
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
model_path = "LinkSoul/Chinese-Llama-2-7b"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_path).half().cuda()
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
instruction = """[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{} [/INST]"""
prompt = instruction.format("用英文回答，什么是夫妻肺片？")
generate_ids = model.generate(tokenizer(prompt, return_tensors='pt').input_ids.cuda(), max_new_tokens=4096, streamer=streamer)
资源下载
我们使用了中英文 SFT 数据集，数据量 1000 万。
如何训练
python train.py --args ...