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
updated
a model
7 days ago
tomasmcm/gpt-oss-11.4b-specialized-all-pruned-moe-only-16-experts-Q4_K_M-GGUF
published
a model
7 days ago
tomasmcm/gpt-oss-11.4b-specialized-all-pruned-moe-only-16-experts-Q4_K_M-GGUF
upvoted
a
collection
11 days ago
GPT-OSS Pruned Experts (4.2B-20B) [IF, Science, Math, etc.]
Organizations
None yet
models
26
tomasmcm/gpt-oss-11.4b-specialized-all-pruned-moe-only-16-experts-Q4_K_M-GGUF
Text Generation
•
11B
•
Updated
•
250
tomasmcm/KwaiCoder-AutoThink-preview-mlx-3Bit
Text Generation
•
5B
•
Updated
•
22
tomasmcm/boltuix-neurobert-mini-onnx
Question Answering
•
Updated
•
3
tomasmcm/NeuroBERT-Mini-ONNX
Fill-Mask
•
Updated
•
2
tomasmcm/nlpconnect-deberta-v3-xsmall-squad2-onnx
Question Answering
•
Updated
•
5
tomasmcm/vmware-deberta-v3-base-mrqa-onnx
Question Answering
•
Updated
•
5
tomasmcm/vmware-tinyroberta-mrqa-onnx
Question Answering
•
Updated
•
4
tomasmcm/vmware-deberta-v3-xsmall-mrqa-onnx
Question Answering
•
Updated
•
4
tomasmcm/deepset-tinyroberta-squad2-onnx
Question Answering
•
Updated
•
3
tomasmcm/deepset-roberta-base-squad2-onnx
Question Answering
•
Updated
•
3
datasets
0
None public yet