HN Explorer

kkkamur

↗ HN profile [ 18.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: 188M Hindi encoder, 28B tokens, 8K context, 1× RTX 4090 (github.com)

    I wanted to improve Hindi retrieval quality, particularly for longer documents ( as the current architectures don't really have a longer context length ), and was curious how far can I push a 4090 haha :) So I trained a…

    1 points 3
  2. Show HN: Kullback – Synthetic RL Environments from Traces (leibler.dev)

    Yo! Introducing Kullback! It is an harness which takes in your traces and spins up executable environments where you can : 1. Evaluate your agents 2. Find opportunities to improve them 3. Improve them using the…

    1 points 0
  3. Leibler – Post-train models from your production traces (leibler.dev)
    3 points 3