This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-Dp-100mbseed10. It has been trained using TRL. This model was trained with SFT.
Open-weight model · Text generation
arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10
by Francesca Padovani fpadovani/arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10
This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-shuff-dyck-100mbseed10. It has been trained using TRL. This model was trained with SFT.
Parameters125M
Context—
Weights7.0 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 (125M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-shuff-dyck-100mbseed10. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by Francesca Padovani.
Configuration
- Architecture
- GPT2LMHeadModel
- Vocabulary size
- 51,200
- Model type
- gpt2
Identity and Version
- Repository
- fpadovani/arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10
- Publisher
- Francesca Padovani
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 125M parameters
- Languages
- sft, trl
- Revision
- 69049c0d002afab785d4245a26ac2548b0382b98
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
280 files, 7.1 GB in total. The weights are 83 files totalling 7.0 GB in bin, pth, safetensors.
Weights83 files · 7.0 GB
Configuration139 files · 86.9 MB
Tokenizer56 files · 42.7 MB
Documentation1 file · 1.9 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-100000/model.safetensors | Weights | 249.6 MB | d682d28a1cac |
| checkpoint-100000/rng_state.pth | Weights | 14.6 KB | ac6d59aec0c3 |
| checkpoint-100000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-104000/model.safetensors | Weights | 249.6 MB | 130600258694 |
| checkpoint-104000/rng_state.pth | Weights | 14.6 KB | c9f8061b2b57 |
| checkpoint-104000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-106890/model.safetensors | Weights | 249.6 MB | 63293cf2f7bc |
| checkpoint-106890/rng_state.pth | Weights | 14.6 KB | ed4c6c956374 |
| checkpoint-106890/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-12000/model.safetensors | Weights | 249.6 MB | c920a2554d4a |
| checkpoint-12000/rng_state.pth | Weights | 14.6 KB | c7fab474e751 |
| checkpoint-12000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-16000/model.safetensors | Weights | 249.6 MB | d31717cd9e5b |
| checkpoint-16000/rng_state.pth | Weights | 14.6 KB | 441e3a628fe5 |
| checkpoint-16000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-20000/model.safetensors | Weights | 249.6 MB | 0d665ea4fcf9 |
| checkpoint-20000/rng_state.pth | Weights | 14.6 KB | 2ce568602dd6 |
| checkpoint-20000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-24000/model.safetensors | Weights | 249.6 MB | 7f6a9ed69eaf |
| checkpoint-24000/rng_state.pth | Weights | 14.6 KB | 7cd6a7618367 |
| checkpoint-24000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-28000/model.safetensors | Weights | 249.6 MB | a3f79c481e89 |
| checkpoint-28000/rng_state.pth | Weights | 14.6 KB | cb1aa4f1a127 |
| checkpoint-28000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-32000/model.safetensors | Weights | 249.6 MB | 65602dabf9d0 |
| checkpoint-32000/rng_state.pth | Weights | 14.6 KB | cbdc71090d02 |
| checkpoint-32000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-36000/model.safetensors | Weights | 249.6 MB | f4cd6d47547b |
| checkpoint-36000/rng_state.pth | Weights | 14.6 KB | 39de1e3d5f4f |
| checkpoint-36000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-4000/model.safetensors | Weights | 249.6 MB | 5f3865577e2f |
| checkpoint-4000/rng_state.pth | Weights | 14.6 KB | 08dfb8e5c33b |
| checkpoint-4000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-40000/model.safetensors | Weights | 249.6 MB | c7c920571619 |
| checkpoint-40000/rng_state.pth | Weights | 14.6 KB | 1323b419ecf7 |
| checkpoint-40000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-44000/model.safetensors | Weights | 249.6 MB | 544f17e82b64 |
| checkpoint-44000/rng_state.pth | Weights | 14.6 KB | 1f546be62d3b |
| checkpoint-44000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-48000/model.safetensors | Weights | 249.6 MB | 92a43a0cf672 |
| checkpoint-48000/rng_state.pth | Weights | 14.6 KB | 8d00e5222c02 |
| checkpoint-48000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-52000/model.safetensors | Weights | 249.6 MB | be598a99a5d8 |
| checkpoint-52000/rng_state.pth | Weights | 14.6 KB | 196b2098665e |
| checkpoint-52000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-56000/model.safetensors | Weights | 249.6 MB | a4ab41cad223 |
| checkpoint-56000/rng_state.pth | Weights | 14.6 KB | bfc7fb7021ce |
| checkpoint-56000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-60000/model.safetensors | Weights | 249.6 MB | b731d221e7cc |
| checkpoint-60000/rng_state.pth | Weights | 14.6 KB | 840b874a686b |
| checkpoint-60000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-64000/model.safetensors | Weights | 249.6 MB | 2f33b1b47f7d |
| checkpoint-64000/rng_state.pth | Weights | 14.6 KB | ddaf83d99db0 |
| checkpoint-64000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-68000/model.safetensors | Weights | 249.6 MB | 164b5ce51964 |
| checkpoint-68000/rng_state.pth | Weights | 14.6 KB | 16579919a3e1 |
| checkpoint-68000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-72000/model.safetensors | Weights | 249.6 MB | e316b18d75c3 |
| checkpoint-72000/rng_state.pth | Weights | 14.6 KB | 7add0ba713e3 |
| checkpoint-72000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-76000/model.safetensors | Weights | 249.6 MB | 7df881473533 |
| checkpoint-76000/rng_state.pth | Weights | 14.6 KB | a98b3ad243f2 |
| checkpoint-76000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-8000/model.safetensors | Weights | 249.6 MB | b9ceb14f4729 |
| checkpoint-8000/rng_state.pth | Weights | 14.6 KB | cae52a5dd276 |
| checkpoint-8000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-80000/model.safetensors | Weights | 249.6 MB | bb9159d21cfd |
| checkpoint-80000/rng_state.pth | Weights | 14.6 KB | 81885d93b9bc |
| checkpoint-80000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-84000/model.safetensors | Weights | 249.6 MB | 9842d7c8b2bc |
| checkpoint-84000/rng_state.pth | Weights | 14.6 KB | 3f6be0ac2a5c |
| checkpoint-84000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-88000/model.safetensors | Weights | 249.6 MB | f88894fc3e83 |
| checkpoint-88000/rng_state.pth | Weights | 14.6 KB | 3477d1dfcfca |
| checkpoint-88000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-92000/model.safetensors | Weights | 249.6 MB | ec36cc930901 |
| checkpoint-92000/rng_state.pth | Weights | 14.6 KB | 6cb21c62c341 |
| checkpoint-92000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| checkpoint-96000/model.safetensors | Weights | 249.6 MB | e2dc3bc1e346 |
| checkpoint-96000/rng_state.pth | Weights | 14.6 KB | bcbd1eb7e530 |
| checkpoint-96000/training_args.bin | Weights | 6.4 KB | c53627f7666a |
| model.safetensors | Weights | 249.6 MB | 63293cf2f7bc |
| training_args.bin | Weights | 6.4 KB | c53627f7666a |
| added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-100000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-100000/config.json | Configuration | 803 B | — |
| checkpoint-100000/generation_config.json | Configuration | 154 B | — |
| checkpoint-100000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-100000/trainer_state.json | Configuration | 5.7 MB | — |
| checkpoint-104000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-104000/config.json | Configuration | 803 B | — |
| checkpoint-104000/generation_config.json | Configuration | 154 B | — |
| checkpoint-104000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-104000/trainer_state.json | Configuration | 5.9 MB | — |
| checkpoint-106890/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-106890/config.json | Configuration | 803 B | — |
| checkpoint-106890/generation_config.json | Configuration | 154 B | — |
| checkpoint-106890/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-106890/trainer_state.json | Configuration | 6.1 MB | — |
| checkpoint-12000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-12000/config.json | Configuration | 803 B | — |
| checkpoint-12000/generation_config.json | Configuration | 154 B | — |
| checkpoint-12000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-12000/trainer_state.json | Configuration | 675.6 KB | — |
| checkpoint-16000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-16000/config.json | Configuration | 803 B | — |
| checkpoint-16000/generation_config.json | Configuration | 154 B | — |
| checkpoint-16000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-16000/trainer_state.json | Configuration | 902.1 KB | — |
| checkpoint-20000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-20000/config.json | Configuration | 803 B | — |
| checkpoint-20000/generation_config.json | Configuration | 154 B | — |
| checkpoint-20000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-20000/trainer_state.json | Configuration | 1.1 MB | — |
| checkpoint-24000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-24000/config.json | Configuration | 803 B | — |
| checkpoint-24000/generation_config.json | Configuration | 154 B | — |
| checkpoint-24000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-24000/trainer_state.json | Configuration | 1.4 MB | — |
| checkpoint-28000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-28000/config.json | Configuration | 803 B | — |
| checkpoint-28000/generation_config.json | Configuration | 154 B | — |
| checkpoint-28000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-28000/trainer_state.json | Configuration | 1.6 MB | — |
| checkpoint-32000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-32000/config.json | Configuration | 803 B | — |
| checkpoint-32000/generation_config.json | Configuration | 154 B | — |
| checkpoint-32000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-32000/trainer_state.json | Configuration | 1.8 MB | — |
| checkpoint-36000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-36000/config.json | Configuration | 803 B | — |
| checkpoint-36000/generation_config.json | Configuration | 154 B | — |
| checkpoint-36000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-36000/trainer_state.json | Configuration | 2.0 MB | — |
| checkpoint-4000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-4000/config.json | Configuration | 803 B | — |
| checkpoint-4000/generation_config.json | Configuration | 154 B | — |
| checkpoint-4000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-4000/trainer_state.json | Configuration | 224.3 KB | — |
| checkpoint-40000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-40000/config.json | Configuration | 803 B | — |
| checkpoint-40000/generation_config.json | Configuration | 154 B | — |
| checkpoint-40000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-40000/trainer_state.json | Configuration | 2.3 MB | — |
| checkpoint-44000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-44000/config.json | Configuration | 803 B | — |
| checkpoint-44000/generation_config.json | Configuration | 154 B | — |
| checkpoint-44000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-44000/trainer_state.json | Configuration | 2.5 MB | — |
| checkpoint-48000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-48000/config.json | Configuration | 803 B | — |
| checkpoint-48000/generation_config.json | Configuration | 154 B | — |
| checkpoint-48000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-48000/trainer_state.json | Configuration | 2.7 MB | — |
| checkpoint-52000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-52000/config.json | Configuration | 803 B | — |
| checkpoint-52000/generation_config.json | Configuration | 154 B | — |
| checkpoint-52000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-52000/trainer_state.json | Configuration | 2.9 MB | — |
| checkpoint-56000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-56000/config.json | Configuration | 803 B | — |
| checkpoint-56000/generation_config.json | Configuration | 154 B | — |
| checkpoint-56000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-56000/trainer_state.json | Configuration | 3.2 MB | — |
| checkpoint-60000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-60000/config.json | Configuration | 803 B | — |
| checkpoint-60000/generation_config.json | Configuration | 154 B | — |
| checkpoint-60000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-60000/trainer_state.json | Configuration | 3.4 MB | — |
| checkpoint-64000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-64000/config.json | Configuration | 803 B | — |
| checkpoint-64000/generation_config.json | Configuration | 154 B | — |
| checkpoint-64000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-64000/trainer_state.json | Configuration | 3.6 MB | — |
| checkpoint-68000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-68000/config.json | Configuration | 803 B | — |
| checkpoint-68000/generation_config.json | Configuration | 154 B | — |
| checkpoint-68000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-68000/trainer_state.json | Configuration | 3.8 MB | — |
| checkpoint-72000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-72000/config.json | Configuration | 803 B | — |
| checkpoint-72000/generation_config.json | Configuration | 154 B | — |
| checkpoint-72000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-72000/trainer_state.json | Configuration | 4.1 MB | — |
| checkpoint-76000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-76000/config.json | Configuration | 803 B | — |
| checkpoint-76000/generation_config.json | Configuration | 154 B | — |
| checkpoint-76000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-76000/trainer_state.json | Configuration | 4.3 MB | — |
| checkpoint-8000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-8000/config.json | Configuration | 803 B | — |
| checkpoint-8000/generation_config.json | Configuration | 154 B | — |
| checkpoint-8000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-8000/trainer_state.json | Configuration | 449.7 KB | — |
| checkpoint-80000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-80000/config.json | Configuration | 803 B | — |
| checkpoint-80000/generation_config.json | Configuration | 154 B | — |
| checkpoint-80000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-80000/trainer_state.json | Configuration | 4.5 MB | — |
| checkpoint-84000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-84000/config.json | Configuration | 803 B | — |
| checkpoint-84000/generation_config.json | Configuration | 154 B | — |
| checkpoint-84000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-84000/trainer_state.json | Configuration | 4.8 MB | — |
| checkpoint-88000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-88000/config.json | Configuration | 803 B | — |
| checkpoint-88000/generation_config.json | Configuration | 154 B | — |
| checkpoint-88000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-88000/trainer_state.json | Configuration | 5.0 MB | — |
| checkpoint-92000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-92000/config.json | Configuration | 803 B | — |
| checkpoint-92000/generation_config.json | Configuration | 154 B | — |
| checkpoint-92000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-92000/trainer_state.json | Configuration | 5.2 MB | — |
| checkpoint-96000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-96000/config.json | Configuration | 803 B | — |
| checkpoint-96000/generation_config.json | Configuration | 154 B | — |
| checkpoint-96000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-96000/trainer_state.json | Configuration | 5.4 MB | — |
| config.json | Configuration | 803 B | — |
| generation_config.json | Configuration | 154 B | — |
| special_tokens_map.json | Configuration | 22.6 KB | — |
| README.md | Documentation | 1.9 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| checkpoint-100000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-100000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-104000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-104000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-106890/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-106890/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-12000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-12000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-16000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-16000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-20000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-20000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-24000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-24000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-28000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-28000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-32000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-32000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-36000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-36000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-4000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-4000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-40000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-40000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-44000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-44000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-48000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-48000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-52000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-52000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-56000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-56000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-60000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-60000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-64000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-64000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-68000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-68000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-72000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-72000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-76000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-76000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-8000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-8000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-80000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-80000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-84000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-84000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-88000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-88000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-92000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-92000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| checkpoint-96000/spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| checkpoint-96000/tokenizer_config.json | Tokenizer | 233.9 KB | — |
| spiece.model | Tokenizer | 1.3 MB | 9689bcf676e0 |
| tokenizer_config.json | Tokenizer | 233.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 7.0 GB
Download from Francesca Padovani
Released by Francesca Padovani through its official repository on Hugging Face.
Built From
- Derived from fpadovani/arb-arab-100mb-ppt-shuff-dyck-100mb_seed10
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 7.0 GB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10
How much GPU memory does arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 need?
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (125M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run arb-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Similar Models
This model is a fine-tuned version of fpadovani/arb-arab-100mb-ppt-shuff-dyck-10mbseed10. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of GeorgeUwaifo/iviegpt2new01cresults on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 4 - evalbatchsize: 8 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupsteps: 387 - numepochs: 5 - mixedprecisiontraining: Native AMP - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1
This model is a custom-code derivative of AxiomicLabs/GPT-X2-125M, adapted for experimental long-context causal language modeling and architecture research. The repository includes a Hugging Face Transformers-compatible GPT-X2 implementation with optional Symplectic Metric-RoPE Governor support and training utilities built around CIxOpt, a heterogeneous optimizer developed for efficient parameter routing across large projection matrices, sensitive normalization parameters, and optional governor modules. The model is intended as a research checkpoint for compact long-context generation, positional encoding experiments, optimizer testing, and continued fine-tuning. This implementation uses a…
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. More details in our paper: https://arxiv.org/abs/2502.02737 SmolLM2 demonstrates significant advances over its predecessor SmolLM1, particularly in instruction following, knowledge, reasoning. The 135M model was trained on 2 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new filtered datasets we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our…
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. More details in our paper https://arxiv.org/abs/2502.02737 SmolLM2 demonstrates significant advances over its predecessor SmolLM1, particularly in instruction following, knowledge, reasoning. The 135M model was trained on 2 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new filtered datasets we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own…