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 Space 4 days ago
NodeLinker/Qwen-3.8-27B-H200 liked a model 4 days ago
AtomicChat/Qwen3.8-27B-GGUF liked a model 4 days ago
Qwen/Qwen3.8-27BOrganizations
None yet
models 28
tomasmcm/Darwin-4B-Genesis-mlx-4Bit
Text Generation • 1B • Updated • 21 • 5
tomasmcm/Baguettotron-mlx-fp16
Text Generation • 0.3B • Updated • 13
tomasmcm/gpt-oss-11.4b-specialized-all-pruned-moe-only-16-experts-Q4_K_M-GGUF
Text Generation • 11B • Updated • 34
tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit
Text Generation • 5B • Updated • 37
tomasmcm/boltuix-neurobert-mini-onnx
Question Answering • Updated • 8
tomasmcm/NeuroBERT-Mini-ONNX
Fill-Mask • Updated • 8
tomasmcm/nlpconnect-deberta-v3-xsmall-squad2-onnx
Question Answering • Updated • 13
tomasmcm/vmware-deberta-v3-base-mrqa-onnx
Question Answering • Updated • 10
tomasmcm/vmware-tinyroberta-mrqa-onnx
Question Answering • Updated • 11
tomasmcm/vmware-deberta-v3-xsmall-mrqa-onnx
Question Answering • Updated • 10
datasets 0
None public yet