Hugging Face's logo
John Locke's picture
🏗️ Building on HF

John Locke

johnlockejrr
100 32 241
seawolf2357's profile picture webxos's profile picture ARUNAGIRINATHAN's profile picture
·

AI & ML interests

OCR, HTR, ATR, NLP, AI

Recent Activity

repliedto jiteshkprasad's post 2 minutes ago
Last week we released Gargi, a 384M English language model trained from scratch on about 17B tokens, roughly 1,000× less training data than Qwen2.5-0.5B (~18T tokens, as published by its authors). What we measured (same harness for every model: lm-evaluation-harness, 0-shot, greedy, each model's start token): - Base model vs Qwen2.5-0.5B: ARC-Easy 62.8 vs 64.7, ARC-Challenge 32.3 vs 32.4, WinoGrande 54.6 vs 56.1. - Chat model: thinking on or off; GSM8K 36.0 with thinking on. - Long inputs: needle-in-a-haystack recall 100% at 8K, 93% at 16K and 90% at 20K tokens, so use it up to about 16K. Where it falls short: knowledge and everyday common sense still scale with data. MMLU is 25.5 vs 47.3, and it trails on HellaSwag and PIQA. It is not a maths specialist, and it is not safety-tuned: put a moderation layer in front of any public use. It runs on a laptop: GGUF (Q8_0 at 410 MB, Q4_K_M, f16) and MLX builds. `ollama run hf.co/udgamlabs/Gargi-GGUF:Q8_0` Apache-2.0 · weights: https://huggingface.co/udgamlabs/Gargi try it: https://udgamlabs.com/models/gargi code: https://github.com/udgamlabs/gargi Named after Gargi Vachaknavi, the Vedic philosopher remembered for asking the hardest questions.
updated a bucket 3 days ago
johnlockejrr/indra-ocr-bucket_v1
published a bucket 3 days ago
johnlockejrr/indra-ocr-bucket_v1
View all activity

Organizations

Samaritan AI's profile picture Syriac AI's profile picture Tiberian AI's profile picture Ethiopic AI's profile picture