Edge RAG LLMs - a tomasmcm Collection

tomasmcm 's Collections

Edge RAG LLMs

updated Apr 15

Lightweight LLMs specialised in RAG based on t5, bart, bert, roberta with ONNX conversion

Upvote

VMware/deberta-v3-base-mrqa

Question Answering • 0.2B • Updated Feb 7 • 6

Note Encoder-only - 184M
tomasmcm/vmware-deberta-v3-base-mrqa-onnx

Question Answering • Updated Apr 15 • 14

Note Score: 7/10 Q4 @ 494.2 MB
teapotai/teapotllm

Text Generation • 0.8B • Updated Apr 19 • 68 • 179

Note Encoder-Decoder - 783M
tomasmcm/teapotai-teapotllm-onnx

Text Generation • Updated Apr 9 • 3 • 1

Note Score: 7/10 Q4 @ 736.9 MB
deepset/tinyroberta-squad2

Question Answering • 0.1B • Updated Sep 26, 2024 • 23k • • 111

Note Encoder-ony - 81.5M
tomasmcm/deepset-tinyroberta-squad2-onnx

Question Answering • Updated Apr 11 • 16

Note Score: 6/10 Q4 @ 186.5 MB
nlpconnect/deberta-v3-xsmall-squad2

Question Answering • Updated Dec 6, 2022 • 9

Note Encoder-only - 22M
tomasmcm/nlpconnect-deberta-v3-xsmall-squad2-onnx

Question Answering • Updated Apr 15 • 13

Note Score: 6/10 Q4 @ 238.5 MB
deepset/roberta-base-squad2

Question Answering • 0.1B • Updated Sep 24, 2024 • 2.56M • • 902

Note Encoder-only - 124M
tomasmcm/deepset-roberta-base-squad2-onnx

Question Answering • Updated Apr 11 • 12

Note Score: 5.5/10 Q4 @ 213.5 MB
allenai/unifiedqa-v2-t5-large-1363200

Updated Jan 24, 2023 • 2.49k • 4

Note Encoder-Decoder - 738M
tomasmcm/allenai-unifiedqa-v2-t5-large-onnx

Text Generation • Updated Apr 10 • 7

Note Score: 5.5/10 Q4 @ 708.2 MB
VMware/tinyroberta-mrqa

Question Answering • 0.1B • Updated Aug 14, 2023 • 7 • 2

Note Encoder-only - 81.5M
tomasmcm/vmware-tinyroberta-mrqa-onnx

Question Answering • Updated Apr 15 • 11

Note Score: 5/10 Q4 @ 186.5 MB
lmqg/bart-large-tweetqa-qa

Text Generation • Updated Dec 8, 2022 • 9

Note Encoder-Decoder - 400M
tomasmcm/lmqg-bart-large-tweetqa-qa-onnx

Text Generation • Updated Apr 10 • 4

Note Score: 4.5/10 Q4 @ 679.4 MB
Salesforce/qaconv-unifiedqa-t5-large

Updated Jan 14 • 32

Note Encoder-Decoder - 738M
tomasmcm/salesforce-qaconv-unifiedqa-t5-large-onnx

Text Generation • Updated Apr 10 • 4

Note Score: 4.5/10 Q4 @ 708.2 MB
Intel/dynamic_tinybert

Question Answering • Updated Mar 22, 2024 • 1.53k • • 82

Note Encoder-only - 66M
tomasmcm/intel-dynamic-tinybert-onnx

Question Answering • Updated Apr 11 • 16

Note Score: 3.5/10 Q4 @ 123 MB
ansukla/task-llm

Text Generation • Updated Jan 26, 2024 • 9

Note Encoder-Decoder - 400M
tomasmcm/ansukla-task-llm-onnx

Text Generation • Updated Apr 10 • 4

Note Score: 3/10 Q4 @ 679.4 MB
lmqg/t5-large-tweetqa-qa

Text Generation • Updated Dec 7, 2022 • 5

Note Encoder-Decoder - 738M
tomasmcm/lmqg-t5-large-tweetqa-qa-onnx

Text Generation • Updated Apr 10 • 3

Note Score: 3/10 Q4 @ 708 MB
gsarti/cora_mgen

Text Generation • Updated Jan 23, 2024 • 8 • 2

Note Encoder-Decoder - 580M
tomasmcm/gsarti-cora-mgen-onnx

Text Generation • Updated Apr 10 • 5

Note Score: 3/10 Q4 @ 1.8 GB

Upvote