These language model checkpoints are trained at the 360M and 1.3Bn parameter scales for up to 50Bn tokens on the Pile corpus, for research purposes.
HazyResearch
community
AI & ML interests
None defined yet.
Collections
3
models
22
hazyresearch/my-awesome-model
Updated
•
11
hazyresearch/JRT-1B-50B
Updated
•
1
hazyresearch/JRT-360M-30B
Updated
•
4
hazyresearch/mamba-360M-30B
Updated
•
1
hazyresearch/based-360M-30B
Updated
•
5
hazyresearch/attn-360M-30B
Updated
•
3
hazyresearch/M2-BERT-8k-Retrieval-Encoder-V1
Fill-Mask
•
Updated
•
20
•
2
hazyresearch/M2-BERT-2k-Retrieval-Encoder-V1
Fill-Mask
•
Updated
•
17
•
1
hazyresearch/M2-BERT-32K-Retrieval-Encoder-V1
Fill-Mask
•
Updated
•
21
•
1
hazyresearch/M2-BERT-128-Retrieval-Encoder-V1
Fill-Mask
•
Updated
•
6
•
1
datasets
14
hazyresearch/based_nq_1024
Viewer
•
Updated
•
3.16k
•
2
hazyresearch/based_nq_512
Viewer
•
Updated
•
3.16k
•
2
hazyresearch/based_nq_2048
Viewer
•
Updated
•
3.16k
•
41
hazyresearch/based_triviaqa
Viewer
•
Updated
•
1.69k
•
34
hazyresearch/based_drop
Viewer
•
Updated
•
2.09k
•
37
hazyresearch/based-squad
Viewer
•
Updated
•
2.98k
•
683
hazyresearch/based-swde
Viewer
•
Updated
•
1.11k
•
2
•
3
hazyresearch/based-fda
Viewer
•
Updated
•
1.1k
•
884
•
3
hazyresearch/LoCoV1-Queries
Viewer
•
Updated
•
7.73k
•
148
•
1
hazyresearch/LoCoV1-Documents
Viewer
•
Updated
•
14.8k
•
148
•
3