Issues
- 1
- 1
chinese-llama-2-7b.ipynb出错求助
#52 opened by leoring123 - 0
- 1
有人遇到过这个报错吗,我的flash_attn版本是2.3.0,跪求大佬指点。ImportError: cannot import name 'flash_attn_unpadded_qkvpacked_func' from 'flash_attn.flash_attn_interface'
#58 opened by SoseloX - 0
requirements.txt
#59 opened by jiangbinbin-code - 2
使用项目中的api.py启动模型,没做4bit量化,使用v100的卡,推理特别慢,经常卡住
#51 opened by jcxian - 1
- 2
训练的数据集格式是啥
#53 opened by 631068264 - 2
ileNotFoundError: Directory LinkSoul/instruction_merge_set is neither a `Dataset` directory nor a `DatasetDict` directory.
#28 opened by zyxcambridge - 1
datatsetsbug
#30 opened by zyxcambridge - 0
训练时的prompt是什么格式的呢
#57 opened by zozoteacher - 0
继续微调
#55 opened by hallucination11 - 0
你好,请问怎么实现公网的api呢
#54 opened by 15899885850 - 2
4bit量化后的模型为什么这么大
#31 opened by liuyukid - 0
- 2
快速测试代码段OOM
#36 opened by LiuZhihhxx - 0
请教一下用open-api-server跟inference-hf 回答问题不一致的问题
#49 opened by ibmxiang - 0
为什么7b模型有26G,原始llama2 7b模型只有13G
#44 opened by secain - 1
怎么从本地直接加载模型啊
#46 opened by JACKzhuz - 0
请教一下公开模型的训练细节
#47 opened by shichao-wang - 0
when I try to train the model, Can't load the configuration of '/PATH/TO/TRANSFORMERS/VERSION/LLAMA2'
#43 opened by githubtianya - 0
调lora需要多少资源
#42 opened by liaoweiguo - 0
有更大的模型吗,33B,70B
#41 opened by liaoweiguo - 0
这个是不是还没进行词表扩充
#19 opened by longgui0318 - 0
huggingface上模型是openrail协议,项目上是apache2,不一致在哪
#39 opened by wzg-zhuo - 2
有流的返回方式吗?
#34 opened by tianlichunhong - 0
- 5
能否做个API接口程序呢?非常感谢!
#8 opened by stuarthe - 0
OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like LinkSoul/Chinese-Llama-2-7b is not the path to a directory containing a file named config.json. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.
#33 opened by hxujal - 0
- 0
数据集中中文样本数量
#29 opened by pangwenfeng - 0
卡住了
#27 opened by zyxcambridge - 1
训练资源
#18 opened by DavidYanAnDe - 1
- 1
Traditional Chinese
#12 opened by compustar - 6
您好,关于 训练和推理,有建议的服务器配置吗?
#2 opened by willqq - 0
请问flash attention 用的是v1吗,是什么版本啊
#16 opened by lllyyyqqq - 4
ggmlv
#7 opened by 13331112522 - 1
什么时候开源训练代码?
#1 opened by Young2019