This model is a fine-tuned version of fpadovani/eng-latn-10mb-ppt-Dp-100mb-packedseed3407. It has been trained using TRL. This model was trained with SFT.
Open-weight model · Text generation
heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10
by Francesca Padovani francesca9805/heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10
heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10 is an open-weight model for text generation from Francesca Padovani. It has 39M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This model is a fine-tuned version of goldfish-models/hebhebr10mb. It has been trained using TRL. This model was trained with SFT.
Parameters39M
Context—
Weights156.4 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10 (39M 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 | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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 Oct 7, 2026.
Model Card
This model is a fine-tuned version of goldfish-models/hebhebr10mb. 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
- francesca9805/heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10
- Publisher
- Francesca Padovani
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 39M parameters
- Languages
- sft, trl
- Revision
- 96174ae949fcc585a22d5ba616278b5391e0de82
- First published
- 2026-09-23
- Last updated
- 2026-09-23
Files and Weights
19 files, 159.6 MB in total. The weights are 5 files totalling 156.4 MB in bin, pth, safetensors.
Weights5 files · 156.4 MB
Configuration8 files · 130.5 KB
Tokenizer4 files · 3.0 MB
Documentation1 file · 1.8 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-500/model.safetensors | Weights | 78.2 MB | c4c9b0cdca17 |
| checkpoint-500/rng_state.pth | Weights | 14.2 KB | 53533f791377 |
| checkpoint-500/training_args.bin | Weights | 5.9 KB | 8c331ad0f6c8 |
| model.safetensors | Weights | 78.2 MB | c4c9b0cdca17 |
| training_args.bin | Weights | 5.9 KB | 8c331ad0f6c8 |
| added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-500/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-500/config.json | Configuration | 801 B | — |
| checkpoint-500/generation_config.json | Configuration | 154 B | — |
| checkpoint-500/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-500/trainer_state.json | Configuration | 28.1 KB | — |
| config.json | Configuration | 801 B | — |
| special_tokens_map.json | Configuration | 22.6 KB | — |
| README.md | Documentation | 1.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| checkpoint-500/spiece.model | Tokenizer | 1.3 MB | 097779febe3e |
| checkpoint-500/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| spiece.model | Tokenizer | 1.3 MB | 097779febe3e |
| tokenizer_config.json | Tokenizer | 233.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 156.4 MB
Download from Francesca Padovani
Released by Francesca Padovani through its official repository on Hugging Face.
Built From
- Derived from goldfish-models/heb_hebr_10mb
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 156.4 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10
How much GPU memory does heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_seed10 need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (39M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run heb-hebr-10mb-ppt-Dp-10mb-packed-bfd_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/eng-latn-10mb-ppt-Dp-10mb-packedseed3407. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of goldfish-models/swalatn10mb. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of goldfish-models/swalatn10mb. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of goldfish-models/swalatn10mb. It has been trained using TRL. This model was trained with SFT.
Model · Text generation
rus-cyrl-10mb-after-ppt-Dp-100mb-packed-bfdiso-ckpt500_seed10
This model is a fine-tuned version of francesca9805/rus-cyrl-10mb-ppt-Dp-100mb-packed-bfdisoseed10. It has been trained using TRL. This model was trained with SFT.