Lightweight LLMs specialised in RAG based on t5, bart, bert, roberta with ONNX conversion
Tomás Marques
tomasmcm
AI & ML interests
Solutions Architect @ whitesmith.co ✦ Creative Technologist (Interaction Designer, Developer, Strategic Innovator)
Recent Activity
liked a model about 17 hours ago
alexintosh/Qwen3.5-35B-A3B-Q4-FlashMoE new activity about 17 hours ago
alexintosh/Qwen3.5-122B-A10B-Q4-FlashMoE:Missing files? liked a model about 23 hours ago
chromadb/context-1Organizations
None yet
models 27
tomasmcm/Baguettotron-mlx-fp16
Text Generation • 0.3B • Updated • 69
tomasmcm/gpt-oss-11.4b-specialized-all-pruned-moe-only-16-experts-Q4_K_M-GGUF
Text Generation • 11B • Updated • 22
tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit
Text Generation • 5B • Updated • 5
tomasmcm/boltuix-neurobert-mini-onnx
Question Answering • Updated • 1
tomasmcm/NeuroBERT-Mini-ONNX
Fill-Mask • Updated
tomasmcm/nlpconnect-deberta-v3-xsmall-squad2-onnx
Question Answering • Updated • 4
tomasmcm/vmware-deberta-v3-base-mrqa-onnx
Question Answering • Updated
tomasmcm/vmware-tinyroberta-mrqa-onnx
Question Answering • Updated • 2
tomasmcm/vmware-deberta-v3-xsmall-mrqa-onnx
Question Answering • Updated • 2
tomasmcm/deepset-tinyroberta-squad2-onnx
Question Answering • Updated
datasets 0
None public yet