iris

Results 11 issues of iris

fudan出的这个dataset链接无法访问

对于初学者来说,理论到实现还是一个鸿沟,up主可不可以考虑将这些求解方法用python一步步实现一下?结合简单的数据集进行分类,或者结合现有的框架和库,比如tensorflow,sklearn。 看了你讲的SVM章,确实看西瓜书变得顺利了,但是发现现实中利用二次规划算法来求解模型的很少,所以实际操作的时候还是觉得力不从心,无从下手。如果up主能讲讲怎么和现有实际数据结合那就更好啦!

Is km-anonymity a little bit different from k-anonymity ?

我在hugging face[GLM-130B](https://huggingface.co/spaces/THUDM/GLM-130B)上体验了以下翻译任务,发现回答根本没办法看,我又把同样的问题到内测版本的chatglm上 https://chatglm.cn/ 试了下,很明显后者和前者不是一个档次。 所以说chat模型和预训练模型中间还做了很多工作吗?不是直接由问题生成的答案吗?

I cannot find any code to define the wandb to visulize the training process in train.py. Can anyone answer my question?

在finetune.py内,def data_collator的第38行生成labels时,作者的做法是: `labels = ( [-100] * (seq_len - 1) + ids[(seq_len - 1) :] + [-100] * (longest - ids_l) )` 我怎么觉得这里有点问题?labels不应该是target_sequence[start+1:]吗,我理解这里ids[seq_len-1]还属于source sequence的最后一个token,其实更应该是target sequence的第二个字符? 有人觉得这里会有疑问吗?

I read about the tutorial of using Transformer to translate the pt to en in [tutorial](https://www.tensorflow.org/text/tutorials/transformer). In the data pipeline construction part : ```python MAX_TOKENS=128 def prepare_batch(pt, en): pt =...

### What is the issue? I installed the Ollama in my linux server according to the official documents: `curl -fsSL https://ollama.com/install.sh | sh` Installation is ok and it returns: `...

bug
nvidia
gpu

in bm25.py file, the code raise the following bug: ` File "/opt/conda/envs/RAG/lib/python3.10/site-packages/llama_index/vector_stores/elasticsearch.py", line 246, in _create_index_if_not_exists if await self.client.indices.exists(index=index_name): TypeError: object HeadApiResponse can't be used in 'await' expression` I think...

I think how to evaluate the RAG performance is vital, please add more content in this chapter