-
### Describe the issue
I exported my medium Whisper model correctly. It could run the inference with the correct answer. After that, I optimized my model. I ran the command line: `python -m onnxrunti…
-
I completed all setup that are Python, tensorflow, pytorch library , ubuntu terminal, dataset downloaded and used Jupyter notebook.But there are some errors when i run the code.Errors like " ModuleNo…
-
Running sentence-transformers on a CPU for various tasks is also possible, especially for consumer-grade libraries, etc. People are running these models w/o any GPU acceleration, which might be good t…
-
Hi there 👋
Let's translate the course to Romanian so that the whole community can benefit from this resource 🌎!
Below are the chapters and files that need translating - let us know here if y…
-
Dear Dr. Han and Dr. Ye,
I have been greatly impressed by your work on the Agent Attention model, as detailed in your recent publication and the associated GitHub repository. The method of integrat…
-
### Feature request
We try to propose the addition of a new and widely-adopted scheduler strategy for language model pretraining in the Transformers repository. Upon reviewing the current schedulers …
-
All other libraries for language models load the model in default model quantization unless explicitly specified. https://github.com/unslothai/unsloth/blob/27fa021a7bb959a53667dd4e7cdb9598c207aa0d/uns…
-
这是我的文件结构图,里面已经把模型下载好了
![image](https://github.com/InternLM/InternLM-XComposer/assets/68574922/b9c7397b-dbc3-42c8-85bb-e91b8d591f43)
但我用怕跑的时候报这个错误
/home/shf/anaconda3/envs/llama/bin/python /media/sh…
-
Hi,
There's been serious issues, still unresolved at this point, with merging qLora adapters easily and accurately without losing perplexity and finetuning quality. See https://github.com/huggingfa…
-
Your version of transformers forces LlamaFlashAttention2 in the constructor of LlamaDecoderLayer in transformers/models/llama/modeling_llama.py which requires Ampere or newer to work. Just by using th…