Nemotron-Personas-UK: one million synthetic personas aligned to the real UK population
• 2
AI & ML interests
The AI computer company based in London
Recent Activity
Papers
View all Papers Articles
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 • 15 -
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored
Text Generation • 4B • Updated • 6 -
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE
Text Generation • 4B • Updated • 139 -
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored
Text Generation • 4B • Updated • 5
Jupiter-G model
A collection of bidirectional datasets containing Welsh-English parallel sentences in chat format, designed for fine-tuning language models
Capability targeted compression of Nemotron 3.5 Lightning using our SPACE compression algorithm
-
locailabs/Juno-N-Coder-25B-A3B
Text Generation • 25B • Updated • 118 • 6 -
locailabs/Juno-N-Coder-25B-A3B-FP8
Text Generation • 25B • Updated • 33 • 2 -
locailabs/Juno-N-Coder-25B-A3B-GGUF
Text Generation • 25B • Updated • 136 • 2 -
locailabs/Juno-N-Coder-25B-A3B-NVFP4
Text Generation • 14B • Updated • 168 • 2
Jupiter-N model and training data
Locai L1-Large model release
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 • 15 -
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored
Text Generation • 4B • Updated • 6 -
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE
Text Generation • 4B • Updated • 139 -
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored
Text Generation • 4B • Updated • 5
Capability targeted compression of Nemotron 3.5 Lightning using our SPACE compression algorithm
-
locailabs/Juno-N-Coder-25B-A3B
Text Generation • 25B • Updated • 118 • 6 -
locailabs/Juno-N-Coder-25B-A3B-FP8
Text Generation • 25B • Updated • 33 • 2 -
locailabs/Juno-N-Coder-25B-A3B-GGUF
Text Generation • 25B • Updated • 136 • 2 -
locailabs/Juno-N-Coder-25B-A3B-NVFP4
Text Generation • 14B • Updated • 168 • 2
Jupiter-G model
Jupiter-N model and training data
Locai L1-Large model release
A collection of bidirectional datasets containing Welsh-English parallel sentences in chat format, designed for fine-tuning language models