Open-weight model
gpt2_small_expandedbabyLM_100M_exp3_subj_ratio_0p50_mix_0p10_42
by Devika Tiwari devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_subj_ratio_0p50_mix_0p10_42
gpt2_small_expandedbabyLM_100M_exp3_subj_ratio_0p50_mix_0p10_42 is an open-weight model from Devika Tiwari. Its published files total 501.2 MB.
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 256 - evalbatchsize: 256 - lrschedulertype…
Model Card
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 256 - evalbatchsize: 256 - lrschedulertype: linear - lrschedulerwarmupsteps: 4000 - numepochs: 20 - Transformers 4.30.2 - Pytorch 2.11.0+cu130 - Datasets 4.1.1 - Tokenizers 0.13.3
Excerpt from the card by Devika Tiwari.
Configuration
- Architecture
- GPT2LMHeadModel
- Vocabulary size
- 50,257
- Stored precision
- float32
- Model type
- gpt2
Identity and Version
- Repository
- devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_subj_ratio_0p50_mix_0p10_42
- Publisher
- Devika Tiwari
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 31e809c76d3e7a6172b74dd7624c0bd9117b34a3
- First published
- 2026-09-24
- Last updated
- 2026-09-25
Files and Weights
16 files, 501.2 MB in total. The weights are 2 files totalling 497.8 MB in bin.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pytorch_model.bin | Weights | 497.8 MB | 7ad7da13d7e3 |
| training_args.bin | Weights | 5.1 KB | b0313da43f2c |
| all_results.json | Configuration | 406 B | — |
| config.json | Configuration | 751 B | — |
| eval_results.json | Configuration | 227 B | — |
| generation_config.json | Configuration | 119 B | — |
| special_tokens_map.json | Configuration | 99 B | — |
| train_results.json | Configuration | 199 B | — |
| trainer_state.json | Configuration | 24.9 KB | — |
| README.md | Documentation | 1.7 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| .gitignore | Repository | 13 B | — |
| merges.txt | Tokenizer | 456.3 KB | — |
| tokenizer.json | Tokenizer | 2.1 MB | — |
| tokenizer_config.json | Tokenizer | 251 B | — |
| vocab.json | Tokenizer | 798.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 497.8 MB
Released by Devika Tiwari through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 497.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.