🏗️ Building on HF

John Locke

johnlockejrr

·

johnlockejrr

AI & ML interests

OCR, HTR, ATR, NLP, AI

Recent Activity

reacted to badaoui's post with 👍 1 day ago

432 GB of ultra-fast HBM4 and up to 23.3 TB/s of memory bandwidth on a single GPU 🤯. Two weeks ago, we got early access to AMD's new Instinct MI455X, and our first goal was simple: make sure 🤗 Transformers works on day one. Over the past few weeks, we worked closely with the AMD team to validate the platform, enable Flash Attention, add torchcodec support for multimodal models, and resolve issues uncovered during testing. The result: ✅ 99.5% success rate across our 24 core Transformers model architectures - already on par with our daily CI on previous AMD and NVIDIA platforms. The hardware is just as exciting. With 432 GB of HBM per GPU, our early capacity experiments showed more than 3× the concurrent long-context requests compared to MI300, thanks to the much larger KV cache capacity. A huge thanks to the AMD team for the early access and the great collaboration! Read the full blog 👇 https://huggingface.co/blog/badaoui/transformers-on-amd-mi455

liked a model 1 day ago

DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

new activity 11 days ago

deepreinforce-ai/Ornith-1.0-9B:deepreinforce-ai/Ornith-1.0-9B is better than empero-ai/Qwythos-9B-Claude-Mythos-5-1M

View all activity

Organizations

johnlockejrr 's models 51

johnlockejrr/LightOnOCR-2-1B-base-nena-ussr

Image-Text-to-Text • 1B • Updated Mar 16 • 6

johnlockejrr/lagfart_yolo

Updated Feb 25 • 2

johnlockejrr/Qwen2.5-14B-Instruct-mxfp4

Text Generation • 15B • Updated Feb 19 • 18

johnlockejrr/Qwen2.5-7B-Instruct-mxfp4

Text Generation • 1B • Updated Feb 19 • 7

johnlockejrr/Qwen2.5-Coder-14b-mxfp4

Text Generation • 15B • Updated Feb 19 • 47 • 1

johnlockejrr/GLM-OCR-samaritan

Image-to-Text • 1B • Updated Feb 15 • 22 • 1

johnlockejrr/LightOnOCR-2-1B-base-samaritan

Image-Text-to-Text • 1B • Updated Feb 14 • 8

johnlockejrr/LightOnOCR-2-1B-base-samaritan-GGUF

Image-Text-to-Text • 0.6B • Updated Feb 13 • 29

johnlockejrr/Nordic_Multicentury

Object Detection • Updated Jan 4 • 10 • 1

johnlockejrr/marianmt_syr_voc_eastern

Translation • 0.2B • Updated Nov 15, 2025 • 14

johnlockejrr/marianmt_heb_voc

Translation • 61.4M • Updated Nov 10, 2025 • 2

johnlockejrr/marianmt_syr_voc_western

Translation • 0.2B • Updated Nov 10, 2025 • 9

johnlockejrr/marianmt-smp-sam-onnx

Translation • Updated Nov 2, 2025 • 6

johnlockejrr/marianmt-smp-sam

Translation • 61.4M • Updated Nov 2, 2025 • 3

johnlockejrr/aramaic-diacritization-model

61.4M • Updated Jul 30, 2025 • 2

johnlockejrr/opus-arc-targum-vocalization

61.4M • Updated Jul 25, 2025 • 1

johnlockejrr/marianmt-he2arc-targum-voc-shva

Translation • 61.4M • Updated Jul 22, 2025 • 5

johnlockejrr/marianmt-he2arc-targum-voc

Translation • 61.4M • Updated Jul 22, 2025 • 3 • 1

johnlockejrr/marianmt-he2yid-tanakh

Translation • 77.1M • Updated Jul 21, 2025 • 3 • 1

johnlockejrr/marianmt-he2arc-targum

Translation • 61.4M • Updated Jul 15, 2025 • 1 • 1

johnlockejrr/marianmt-he2arc-sam

Translation • 61.4M • Updated Jul 15, 2025 • 1 • 1

johnlockejrr/marianmt-en2he-nwt

77.9M • Updated Jul 14, 2025 • 2 • 1

johnlockejrr/marianmt-he2en-nwt

77.1M • Updated Jul 13, 2025 • 2 • 1

johnlockejrr/opus-mt-arc-heb

77.1M • Updated Jun 25, 2025 • 4

johnlockejrr/eynollah-sam_40_mss-patches

Updated May 10, 2025 • 5

johnlockejrr/eynollah-sam_40_mss-no_patches

Updated May 10, 2025 • 9

johnlockejrr/pylaia-heb_synth_lines_pytorch_2

Text Generation • Updated Apr 30, 2025

johnlockejrr/pylaia-yiddish_synth_pytorch_2

Image-to-Text • Updated Apr 26, 2025 • 1

johnlockejrr/hebrew_sefaria_tokenizer

Updated Apr 22, 2025

johnlockejrr/hebrew_sefaria_preprocessor

Updated Apr 22, 2025