arxiv:2404.07647
Nathan Godey
nthngdy
AI & ML interests
None yet
Organizations
models
30
nthngdy/llama-3b-empty
Updated
•
4
nthngdy/hythia-410m-10k_ft-bs256-lr1e-4-cos-1k
Text Generation
•
Updated
•
13
nthngdy/hythia410m-10k_ft_bs256_500_cos_lr6e-4-probe
Text Generation
•
Updated
•
13
nthngdy/hythia410m-10k_raw
Text Generation
•
Updated
•
9
nthngdy/hythia410m-10k_ft_bs256_500_cst_lr6e-5-rp
Text Generation
•
Updated
•
11
nthngdy/hythia410m-10k_ft_bs256_500_cos_lr6e-5-rp
Text Generation
•
Updated
•
8
nthngdy/hythia410m-10k_ft_bs256_500_cos_lr1e-4-rp
Text Generation
•
Updated
•
9
nthngdy/pythia410m-10k-rp
Text Generation
•
Updated
•
14
nthngdy/hythia160m-2.5k-rp-bs16-lr6e-5-nowt
Text Generation
•
Updated
•
13
nthngdy/pythia160m-2.5k-rp
Text Generation
•
Updated
•
14
datasets
16
nthngdy/mmlu_no_train
Viewer
•
Updated
•
31.7k
•
582
nthngdy/lambada_openai
Viewer
•
Updated
•
5.15k
•
34
nthngdy/crows_pairs_multilingual
Viewer
•
Updated
•
1.68k
•
48
nthngdy/ai2_arc
Viewer
•
Updated
•
7.79k
•
55
nthngdy/piqa
Viewer
•
Updated
•
21k
•
63
nthngdy/hellaswag
Viewer
•
Updated
•
60k
•
47
nthngdy/culturax_fr_metrics
Viewer
•
Updated
•
100k
•
38
nthngdy/pile_small_miniLM
Viewer
•
Updated
•
100k
•
38
nthngdy/babylm_10M
Viewer
•
Updated
•
1.02M
•
35
nthngdy/wikipedia-22-12-concat-split
Viewer
•
Updated
•
93.5M
•
628