🔄 In a Training Loop

Omar Sanseviero

osanseviero

google

·

https://osanseviero.github.io/hackerllama/

AI & ML interests

Llamas, model merging, massive ASR for data collection, 3D ML, on-device ML, quantization, model judging, ML in browser, healthcare applications, education, intersection of art and ML.🦙

Recent Activity

liked a Space 4 days ago

google/gemma4_vision_token_budget

updated a collection 10 days ago

authored a paper 22 days ago

Gemma 4 Technical Report

View all activity

Organizations

New activity in google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant about 1 month ago

Update config.json

#1 opened about 1 month ago by

New activity in google/gemma-4-31B-it-qat-q4_0-unquantized-assistant about 1 month ago

Update config.json

#4 opened about 1 month ago by

New activity in google/gemma-4-12B-it-qat-w4a16-ct about 2 months ago

fix: add missing num_soft_tokens and model_patch_size to vision_config

#5 opened about 2 months ago by

lucianommartins

New activity in google/gemma-4-12B-it-qat-q4_0-gguf about 2 months ago

Update README.md

#1 opened about 2 months ago by

New activity in google/gemma-4-31B-it-qat-q4_0-gguf about 2 months ago

Fix library tag

#1 opened about 2 months ago by

New activity in google/gemma-4-26B-A4B-it-qat-q4_0-gguf about 2 months ago

Fix library tag

#2 opened about 2 months ago by

New activity in google/gemma-4-12B-it about 2 months ago

Wrong context size in config.json?

#10 opened about 2 months ago by

fix max_position_embeddings 128Ki --> 256Ki

#11 opened about 2 months ago by

New activity in google/gemma-4-12B-it-assistant about 2 months ago

Update max_position_embeddings to support full context length.

#2 opened about 2 months ago by

New activity in google/gemma-4-12B about 2 months ago

Update max_position_embeddings to full context length

#4 opened about 2 months ago by

New activity in google/gemma-4-12B-it about 2 months ago

Update max_position_embeddings to full context length

#21 opened about 2 months ago by

New activity in google/gemma-4-E4B-it 2 months ago

[Bug] `enable_thinking` doesn't trigger thinking mode for E4B/E2B

#26 opened 3 months ago by

New activity in google/gemma-4-26B-A4B-it 2 months ago

Add MMMU-Pro evaluation result

#44 opened 2 months ago by

New activity in google/gemma-4-31B-it 2 months ago

Add MMMU-Pro evaluation result

#107 opened 2 months ago by

fix(chat_template): Emit multimodal placeholders in tool response content-parts

#94 opened 3 months ago by

New activity in google/gemma-4-26B-A4B-it 2 months ago

fix(chat_template): Emit multimodal placeholders in tool response content-parts

#38 opened 3 months ago by

New activity in google/gemma-4-E4B-it 2 months ago

fix(chat_template): Emit multimodal placeholders in tool response content-parts

#30 opened 3 months ago by

New activity in google/gemma-4-E2B-it 2 months ago

fix(chat_template): Emit multimodal placeholders in tool response content-parts

#28 opened 3 months ago by

New activity in google/fleurs 3 months ago

Convert dataset to Parquet

#31 opened 7 months ago by

New activity in google/gemma-4-E2B-it 3 months ago

Fix lineage

#31 opened 3 months ago by