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
new activity 1 day ago
ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF:Part 6 of IQ2_XXS is missing? liked a model 1 day ago
ricursiveAI/Ripple-65B-Preview new activity 3 days ago
ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF:fixedOrganizations
None yet
models 28
tomasmcm/Darwin-4B-Genesis-mlx-4Bit
Text Generation • 8B • Updated • 16 • 5
tomasmcm/Baguettotron-mlx-fp16
Text Generation • 0.3B • Updated • 20
tomasmcm/gpt-oss-11.4b-specialized-all-pruned-moe-only-16-experts-Q4_K_M-GGUF
Text Generation • 11B • Updated • 62
tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit
Text Generation • 41B • Updated • 17
tomasmcm/boltuix-neurobert-mini-onnx
Question Answering • Updated • 19
tomasmcm/NeuroBERT-Mini-ONNX
Fill-Mask • Updated • 9
tomasmcm/nlpconnect-deberta-v3-xsmall-squad2-onnx
Question Answering • Updated • 73
tomasmcm/vmware-deberta-v3-base-mrqa-onnx
Question Answering • Updated • 19
tomasmcm/vmware-tinyroberta-mrqa-onnx
Question Answering • Updated • 5
tomasmcm/vmware-deberta-v3-xsmall-mrqa-onnx
Question Answering • Updated • 6
datasets 0
None public yet