Arnav Shah
Arnav Shah
@hydai I am willing to contribute in this project. Can this project be run on base 8gb RAM M1 mac?
@hydai I have tried fine tuning llama-2-7b-chat.Q2_K on my local machine using llama.cpp.
@hydai can you give some resources to read about how to implement functions in wasi-nn ggml plugin please
@RishabhJain2018 can you please assign this one?
@RishabhJain2018 I have written a `ci-cd.yml` workflow file which I tested on my own fork. It builds and runs the frontend and backend tests. For deployment stage there are a...
@RishabhJain2018 apologies for late response. Will raise soon.
Hey @juntao I am interested to work on it . So can we not use [SEC API](https://sec-api.io/ ) here?
For my pre-test, I have taken a dataset which has the question answer pairs on reports of the 2023 SEC-10K for different companies [link](https://huggingface.co/datasets/itzme091/financial-qa-10K-modified2) .I finetuned Phi-3-Mini-4k-instruct (converted to gguf)...
Hey @juntao I have made a python script that can automatically download the filing and parse using Llama-Parse. The file can then be uploaded to huggingface. [link](https://github.com/lazyperson1020/LFX-WasmEdge-PreTask-SEC/blob/main/Parsing%20and%20Uploading%20(1).ipynb)
Dearest @juntao The major issue that I found was the lack of analysis of the reports with specific numbers and values that were given in the reports as TABLES. Thus...