Rajdeep Borgohain's picture

Rajdeep Borgohain

rbgo

AI & ML interests

Solving language barriers.

Recent Activity

upvoted a paper 3 days ago
Qwen2.5 Technical Report
liked a dataset 5 days ago
NTU-NLP-sg/xCodeEval
upvoted a collection 7 days ago
Qwen2.5
View all activity

Organizations

Inferless's profile picture Social Post Explorers's profile picture

rbgo's activity

reacted to m-ric's post with šŸ‘ about 1 month ago
view post
Post
786
šŸ” Meta teams use a fine-tuned Llama model to fix production issues in seconds

One of Meta's engineering teams shared how they use a fine-tuned small Llama (Llama-2-7B, so not even a very recent model) to identify the root cause of production issues with 42% accuracy.

šŸ¤” 42%, is that not too low?
āž”ļø Usually, whenever there's an issue in production, engineers dive into recent code changes to find the offending commit. At Meta's scale (thousands of daily changes), this is like finding a needle in a haystack.
šŸ’” So when the LLM-based suggestion is right, it cuts incident resolution time from hours to seconds!

How did they do it?

šŸ”„ Two-step approach:
ā€£ Heuristics (code ownership, directory structure, runtime graphs) reduce thousands of potential changes to a manageable set
ā€£ Fine-tuned Llama 2 7B ranks the most likely culprits

šŸŽ“ Training pipeline:
ā€£ Continued pre-training on Meta's internal docs and wikis
ā€£ Supervised fine-tuning on past incident investigations
ā€£ Training data mimicked real-world constraints (2-20 potential changes per incident)

šŸ”® Now future developments await:
ā€£ Language models could handle more of the incident response workflow (runbooks, mitigation, post-mortems)
ā€£ Improvements in model reasoning should boost accuracy further

Read it in full šŸ‘‰ https://www.tryparity.com/blog/how-meta-uses-llms-to-improve-incident-response
liked a Space about 2 months ago
reacted to abhishek's post with šŸ‘ 2 months ago
updated a collection 3 months ago
updated a collection 3 months ago