tiny-gpt-chat is an open-weight model from Alex Lin. Its published files total 28.1 MB.
A tiny (~6.9M parameter) GPT trained from scratch: pretrained on TinyStories, then fine-tuned on a few thousand everyday conversations. It can do basic small talk, but it is very small, so expect nonsense and made-up facts.
Model Card
A tiny (~6.9M parameter) GPT trained from scratch: pretrained on TinyStories, then fine-tuned on a few thousand everyday conversations. It can do basic small talk, but it is very small, so expect nonsense and made-up facts. Requires torch, tokenizers and huggingfacehub. message reply. Context length is 256 tokens.
Excerpt from the card by Alex Lin.
Identity and Version
- Repository
- al20312/tiny-gpt-chat
- Publisher
- Alex Lin
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 575bf55c94cde7b840879cc42dd38c9b6b826a46
- First published
- 2026-10-11
- Last updated
- 2026-10-11
Files and Weights
6 files, 28.1 MB in total. The weights are 1 file totalling 27.6 MB in pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.pt | Weights | 27.6 MB | 9dbc58c9f840 |
| config.json | Configuration | 81 B | — |
| model.py | Configuration | 3.3 KB | — |
| README.md | Documentation | 810 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 554.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 27.6 MB
Released by Alex Lin through its official repository on Hugging Face.
Built From
- Trained on (disclosed) HuggingFaceTB/everyday-conversations-llama3.1-2k
- Trained on (disclosed) roneneldan/TinyStories
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 27.6 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.