GPT 2 4096t Scratch 10ep is an open-source language model by tihon-nth. Features: 126.8m LLM, VRAM: 0.5GB, LLM Explorer Score: 0.32.
| LLM Name | GPT 2 4096t Scratch 10ep |
| Repository 🤗 | https://huggingface.co/tihon-nth/gpt-2-4096t-scratch-10ep_ |
| Base Model(s) | |
| Model Size | 126.8m |
| Required VRAM | 0.5 GB |
| Updated | 2026-08-18 |
| Maintainer | tihon-nth |
| Model Type | gpt2 |
| Model Files | |
| Model Architecture | GPT2LMHeadModel |
| Model Max Length | 1024 |
| Transformers Version | 5.8.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 50257 |
| Activation Function | gelu_new |
| Errors | replace |