Animesh Jain

icon company @Microsoft icon location Redmond, WA

Results 2 issues of Animesh Jain

Finetuning code llama for Multi-File code generation on private repository

1 comment

Hello. I'm trying to finetune code llama for a multifile code generation task on my private repository. The goal is to have the LLM generate code for some common bugs...

fine-tuning

Slow Inference on LLAMA 3.1 405B using ollama.generate with Large Code Snippets on multi-H100 GPUs

1 comment

I'm experiencing very slow inference times when using the ollama.generate function on a multiple H100 GPU machine. Specifically, it is taking up to 5 minutes per inference, even though the...