Nemotron-Personas-UK: one million synthetic personas aligned to the real UK population 28 days ago • 4
NEEDLE Backdoored models from the paper: Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published Sep 29 • 9 locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated Oct 2 • 44 locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated Oct 2 • 18 locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated Oct 2 • 6
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published Sep 29 • 9
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated Oct 2 • 44
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated Oct 2 • 18
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated Oct 2 • 6
Jupiter-G Jupiter-G model locailabs/Jupiter-G-8B Any-to-Any • 8B • Updated May 9 • 85 • 5 locailabs/Jupiter-G-8B-GGUF Any-to-Any • 8B • Updated May 9 • 69 • 2
Jupiter-N Training Data locailabs/nemotron_terminal_filtered Viewer • Updated Apr 13 • 30k • 148 • 2 locailabs/nemotron-chat-welsh Viewer • Updated Apr 12 • 27.8k • 50 • 1 locailabs/legislation-gov-uk-en-cy Viewer • Updated Apr 8 • 17.9k • 55 locailabs/cofnodycynulliad_en_cy Viewer • Updated Apr 8 • 19.6k • 40
Welsh-English Parallel Translations A collection of bidirectional datasets containing Welsh-English parallel sentences in chat format, designed for fine-tuning language models locailabs/welsh_parallel_corpora Viewer • Updated Feb 18 • 325k • 51 locailabs/tatoeba_welsh Viewer • Updated Feb 18 • 3.34k • 14 locailabs/eubookshop_welsh Viewer • Updated Feb 18 • 2.12k • 22 locailabs/opensubtitles_welsh Viewer • Updated Feb 18 • 236k • 24
Juno-N Capability targeted compression of Nemotron 3.5 Lightning using our SPACE compression algorithm locailabs/Juno-N-Coder-25B-A3B Text Generation • 25B • Updated Aug 22 • 49 • 6 locailabs/Juno-N-Coder-25B-A3B-FP8 Text Generation • 25B • Updated Aug 22 • 30 • 2 locailabs/Juno-N-Coder-25B-A3B-GGUF Text Generation • 25B • Updated Aug 22 • 107 • 2 locailabs/Juno-N-Coder-25B-A3B-NVFP4 Text Generation • 14B • Updated Aug 22 • 116 • 2
Jupiter-N Jupiter-N model and training data locailabs/Jupiter-N-120B Text Generation • 121B • Updated May 5 • 22 • 5 Jupiter-N Training Data Collection 9 items • Updated Aug 11
Locai L1-Large Locai L1-Large model release locailabs/locai-l1-large-FP8 Text Generation • 235B • Updated Feb 26 • 20 • 1 locailabs/locai-l1-large Text Generation • 235B • Updated Feb 26 • 18 • 8 locailabs/locai-l1-large-2011 Text Generation • 235B • Updated Feb 26 • 12
NEEDLE Backdoored models from the paper: Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published Sep 29 • 9 locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated Oct 2 • 44 locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated Oct 2 • 18 locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated Oct 2 • 6
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published Sep 29 • 9
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated Oct 2 • 44
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated Oct 2 • 18
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated Oct 2 • 6
Juno-N Capability targeted compression of Nemotron 3.5 Lightning using our SPACE compression algorithm locailabs/Juno-N-Coder-25B-A3B Text Generation • 25B • Updated Aug 22 • 49 • 6 locailabs/Juno-N-Coder-25B-A3B-FP8 Text Generation • 25B • Updated Aug 22 • 30 • 2 locailabs/Juno-N-Coder-25B-A3B-GGUF Text Generation • 25B • Updated Aug 22 • 107 • 2 locailabs/Juno-N-Coder-25B-A3B-NVFP4 Text Generation • 14B • Updated Aug 22 • 116 • 2
Jupiter-G Jupiter-G model locailabs/Jupiter-G-8B Any-to-Any • 8B • Updated May 9 • 85 • 5 locailabs/Jupiter-G-8B-GGUF Any-to-Any • 8B • Updated May 9 • 69 • 2
Jupiter-N Jupiter-N model and training data locailabs/Jupiter-N-120B Text Generation • 121B • Updated May 5 • 22 • 5 Jupiter-N Training Data Collection 9 items • Updated Aug 11
Jupiter-N Training Data locailabs/nemotron_terminal_filtered Viewer • Updated Apr 13 • 30k • 148 • 2 locailabs/nemotron-chat-welsh Viewer • Updated Apr 12 • 27.8k • 50 • 1 locailabs/legislation-gov-uk-en-cy Viewer • Updated Apr 8 • 17.9k • 55 locailabs/cofnodycynulliad_en_cy Viewer • Updated Apr 8 • 19.6k • 40
Locai L1-Large Locai L1-Large model release locailabs/locai-l1-large-FP8 Text Generation • 235B • Updated Feb 26 • 20 • 1 locailabs/locai-l1-large Text Generation • 235B • Updated Feb 26 • 18 • 8 locailabs/locai-l1-large-2011 Text Generation • 235B • Updated Feb 26 • 12
Welsh-English Parallel Translations A collection of bidirectional datasets containing Welsh-English parallel sentences in chat format, designed for fine-tuning language models locailabs/welsh_parallel_corpora Viewer • Updated Feb 18 • 325k • 51 locailabs/tatoeba_welsh Viewer • Updated Feb 18 • 3.34k • 14 locailabs/eubookshop_welsh Viewer • Updated Feb 18 • 2.12k • 22 locailabs/opensubtitles_welsh Viewer • Updated Feb 18 • 236k • 24