AstraGPTCoder-7B
Custom Architecture · Custom BPE Tokenizer · Reasoning Fine-Tuned on Dual RTX 4090 Every layer of AstraGPT-7B was...
Метка: custom-tokenizer
Atom3.4m
Atom is a 3.4M parameter causal language model developed by Universal Computing Research. It was pretrained from scratch...
GPT-S-1.4M
GPT-S-1.4M — модель первого поколения в семействе малых моделей GPT-S, построенная на архитектуре T-X3: 1,4M параметров, 6B обучающих...