wj210
wj210
OOM error when loading flan-tf-xxl model for inference. The model was able to load perfectly without deepspeed, just by using the standard code in huggingface transformers. It used approximately 20+...
I encountered some issue with scraping with gnews, these errors are along the lines of `Article `download()` failed with 403 Client Error: Max restarts limit reached for url` `Article `download()`...
I save the model during certain timesteps so at the end of the run i would have multiple checkpoints, the files are saved as ckpt-1000, ckpt-2000 ... If for example,...
Hi, thanks for this useful codebase! Do you have any plans or idea on how the tables can be parsed into readable format? say using pandas etc?
I want to use self-refine for reasoning task, such as open-book qa for example. For the few-shot examples for the initial generation. Does the examples have to be bad examples?...
This error happened while i was trying to import mujoco_py in a docker file, i tried solutions for "x86_64-linux-gnu-gcc" error but it seems the cause of the error is different...
`from finnlp.data_sources.news.finnhub_date_range import Finnhub_Date_Range start_date = "2023-01-01" end_date = "2023-01-02" config = { "use_proxy": "us_free", # use proxies to prvent ip blocking "max_retry": 5, "proxy_pages": 5, "token": "ck22t49r01qng12gonugck22t49r01qng12gonv0" # Available...
Hi, i have inserted some updates into the code to improve speed and also make it compatible with the latest openai API updates. Could you have a look and see...
Hi, i would like to ask if it has been tried out with llama that batch inference works? i followed this https://huggingface.co/docs/transformers/llm_tutorial#wrong-padding-side , where they pass both the input_ids and...
In parallel with #38, tho i am relating to full training instead of lora. When i use a different set of prefs (ie chosen and rejected) but still same instructions...