Merged Goldfish Models, compared to Bilingual Pretrained BGPT
Suchir Salhan
suchirsalhan
AI & ML interests
Multilinguality and Cognitively-Inspired AI. Tokenization, Pretraining, Interpretability & Alignment.
Recent Activity
updated
a dataset
about 23 hours ago
suchirsalhan/babylm-detox
published
a dataset
about 23 hours ago
suchirsalhan/babylm-detox
updated
a dataset
2 days ago
ALTACambridge/CAFe
Organizations
models
197
suchirsalhan/llama-3.1-8b-instruct-lora-A2
Updated
suchirsalhan/llama-3.1-8b-instruct-lora-A1
Updated
suchirsalhan/stablelm-zephyr-3b-lora-C1
Updated
suchirsalhan/stablelm-zephyr-3b-lora-B2
Updated
suchirsalhan/stablelm-zephyr-3b-lora-B1
Updated
suchirsalhan/stablelm-zephyr-3b-lora-A2
Updated
suchirsalhan/stablelm-zephyr-3b-lora-A1
Updated
suchirsalhan/unimix-ru_uk-xlm-roberta-base
Updated
suchirsalhan/unimix-es_vi-xlm-roberta-base
Updated
suchirsalhan/unimix-es_tr-xlm-roberta-base
Updated
datasets
7
suchirsalhan/babylm-detox
Viewer
•
Updated
•
11.1M
•
15
suchirsalhan/gptbert-tokenised
Updated
•
10
suchirsalhan/Phonemized-UD
Viewer
•
Updated
•
1.19M
•
239
suchirsalhan/BabyLM-Pretokenised
Viewer
•
Updated
•
1.64M
•
20
suchirsalhan/MAO-CHILDES
Viewer
•
Updated
•
3.81M
•
12
suchirsalhan/CLiMP
Preview
•
Updated
•
19
•
1
suchirsalhan/SLING
Viewer
•
Updated
•
40k
•
82