9 27 20

Rajdeep Borgohain

rbgo

RajdeepBorgohain

AI & ML interests

Solving language barriers.

Recent Activity

Reacted to m-ric's post with 👍 3 days ago

🔍 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. 🤔 42%, is that not too low? ➡️ 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. 💡 So when the LLM-based suggestion is right, it cuts incident resolution time from hours to seconds! How did they do it? 🔄 Two-step approach: ‣ Heuristics (code ownership, directory structure, runtime graphs) reduce thousands of potential changes to a manageable set ‣ Fine-tuned Llama 2 7B ranks the most likely culprits 🎓 Training pipeline: ‣ Continued pre-training on Meta's internal docs and wikis ‣ Supervised fine-tuning on past incident investigations ‣ Training data mimicked real-world constraints (2-20 potential changes per incident) 🔮 Now future developments await: ‣ Language models could handle more of the incident response workflow (runbooks, mitigation, post-mortems) ‣ Improvements in model reasoning should boost accuracy further Read it in full 👉 https://www.tryparity.com/blog/how-meta-uses-llms-to-improve-incident-response

updated a dataset 13 days ago

rbgo/llm-inference-benchmark

liked a Space 26 days ago

lj1995/GPT-SoVITS-v2

View all activity

Organizations

rbgo's activity

liked a Space 26 days ago

Running on Zero

🤗

GPT SoVITS V2

liked a Space about 2 months ago

Running

🥇

LLM Inference Benchmark

liked a model 7 months ago

NousResearch/Hermes-2-Pro-Llama-3-8B

Text Generation • Updated Sep 14 • 32.2k • 407

liked 2 models 8 months ago

CohereForAI/c4ai-command-r-plus

Text Generation • Updated Sep 27 • 3.87k • 1.68k

unsloth/mistral-7b-v0.2

Text Generation • Updated Sep 11 • 460 • 23

liked a Space 9 months ago

Running on Zero

841

🥼👖👗

OOTDiffusion

High-quality virtual try-on ~ Your cyber fitting room

liked a model 9 months ago

Inferless/Mixtral-8x7B-v0.1-int8-GPTQ

Text Generation • Updated Jan 25 • 57 • 2

liked 2 Spaces 9 months ago

Build error

⚡

SMPLer X

Running

🐨

LDB

liked a model 9 months ago

Inferless/SOLAR-10.7B-Instruct-v1.0-GPTQ

Text Generation • Updated Jan 4 • 10 • 2

liked a dataset 10 months ago

snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset

Viewer • Updated Jan 23 • 62.7k • 115 • 42

liked 2 models 10 months ago

Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct

Text Generation • Updated Feb 7 • 191 • 13

tenyx/TenyxChat-8x7B-v1

Text Generation • Updated Jan 19 • 1.25k • 12

liked a dataset 10 months ago

argilla/distilabel-intel-orca-dpo-pairs

Viewer • Updated Feb 5 • 12.9k • 925 • 167

liked a Space 10 months ago

Running on CPU Upgrade

11.8k

🏆

Open LLM Leaderboard 2

Track, rank and evaluate open LLMs and chatbots

liked a model 10 months ago

mistralai/Mixtral-8x7B-v0.1

Text Generation • Updated Jul 24 • 59.5k • 1.65k

liked a dataset over 1 year ago

liuhaotian/LLaVA-Instruct-150K

Preview • Updated Jan 3 • 3k • 460

liked a Space over 1 year ago

Paused

517

🦙

StableVicuna

liked a Space almost 2 years ago

Configuration error

☃️

SnowballFight

liked a Space over 2 years ago

Runtime error

🐨