Linearizing LLMs with high quality and efficiency. We linearize the full Llama 3.1 model family -- 8b, 70b, 405b -- for the first time!
HazyResearch
community
AI & ML interests
None defined yet.
Recent Activity
models
26
hazyresearch/lolcats-llama-3.1-405b
Updated
•
3
•
11
hazyresearch/lolcats-llama-3.1-70b
Updated
•
1
•
4
hazyresearch/lolcats-llama-3.1-8b-ft-lora
Updated
•
7
•
2
hazyresearch/lolcats-llama-3.1-8b-distill
Text Generation
•
Updated
•
16
•
14
hazyresearch/my-awesome-model
Updated
•
1
•
2
hazyresearch/JRT-1B-50B
Updated
•
15
hazyresearch/JRT-360M-30B
Updated
•
86
hazyresearch/mamba-360M-30B
Updated
•
130
hazyresearch/based-360M-30B
Updated
•
73
hazyresearch/attn-360M-30B
Updated
•
91
datasets
18
hazyresearch/GPQA_GPT-4o
Viewer
•
Updated
•
646
•
14
hazyresearch/GPQA_GPT-4o-mini
Viewer
•
Updated
•
646
•
15
hazyresearch/GSM8K_GPT-4o-mini_with_LM_Judges_and_RMs_v1
Viewer
•
Updated
•
127
•
27
hazyresearch/smoothie_data
Preview
•
Updated
•
7
•
1
hazyresearch/based_nq_1024
Viewer
•
Updated
•
3.16k
•
52
hazyresearch/based_nq_512
Viewer
•
Updated
•
3.16k
•
45
hazyresearch/based_nq_2048
Viewer
•
Updated
•
3.16k
•
66
hazyresearch/based_triviaqa
Viewer
•
Updated
•
1.69k
•
111
hazyresearch/based_drop
Viewer
•
Updated
•
2.09k
•
116
hazyresearch/based-squad
Viewer
•
Updated
•
2.98k
•
646
•
1