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
zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407
by Francesca Padovani francesca9805/zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407
zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 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 francesca9805/zho-hans-10mb-ppt-Dp-10mb-packed-bfdisoseed3407. It has been trained using TRL. This model was trained with SFT.
Parameters39M
Context—
Weights782.0 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 (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 francesca9805/zho-hans-10mb-ppt-Dp-10mb-packed-bfdisoseed3407. 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/zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407
- Publisher
- Francesca Padovani
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 39M parameters
- Languages
- trl, sft
- Revision
- a84abcbecf73d3223881ceceb0b10744c1fabb44
- First published
- 2026-10-02
- Last updated
- 2026-10-02
Files and Weights
99 files, 797.4 MB in total. The weights are 29 files totalling 782.0 MB in bin, pth, safetensors.
Weights29 files · 782.0 MB
Configuration48 files · 1.8 MB
Tokenizer20 files · 13.7 MB
Documentation1 file · 2.0 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-1000/model.safetensors | Weights | 78.2 MB | 8f01620c3fe5 |
| checkpoint-1000/rng_state.pth | Weights | 14.6 KB | e83fdc20cfc8 |
| checkpoint-1000/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-1500/model.safetensors | Weights | 78.2 MB | 30beff5d64b0 |
| checkpoint-1500/rng_state.pth | Weights | 14.6 KB | 108daf965509 |
| checkpoint-1500/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-2000/model.safetensors | Weights | 78.2 MB | 37c41d83de51 |
| checkpoint-2000/rng_state.pth | Weights | 14.6 KB | 563606b54b61 |
| checkpoint-2000/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-2500/model.safetensors | Weights | 78.2 MB | 56badad2b5d3 |
| checkpoint-2500/rng_state.pth | Weights | 14.6 KB | f0f61d4a5f76 |
| checkpoint-2500/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-3000/model.safetensors | Weights | 78.2 MB | 2a14c5e21777 |
| checkpoint-3000/rng_state.pth | Weights | 14.6 KB | 38618f19e517 |
| checkpoint-3000/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-3500/model.safetensors | Weights | 78.2 MB | 67c4cdcd1d18 |
| checkpoint-3500/rng_state.pth | Weights | 14.6 KB | 7288894dba5a |
| checkpoint-3500/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-4000/model.safetensors | Weights | 78.2 MB | fe9109d82115 |
| checkpoint-4000/rng_state.pth | Weights | 14.6 KB | 4140060b3ccf |
| checkpoint-4000/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-4500/model.safetensors | Weights | 78.2 MB | 9f69ae76304f |
| checkpoint-4500/rng_state.pth | Weights | 14.6 KB | e3a0eeab5322 |
| checkpoint-4500/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| checkpoint-500/model.safetensors | Weights | 78.2 MB | 5090be54bf10 |
| checkpoint-500/rng_state.pth | Weights | 14.6 KB | f9eb80c89a85 |
| checkpoint-500/training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| model.safetensors | Weights | 78.2 MB | 9f69ae76304f |
| training_args.bin | Weights | 6.4 KB | 7495c9ec84d0 |
| added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-1000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-1000/config.json | Configuration | 801 B | — |
| checkpoint-1000/generation_config.json | Configuration | 154 B | — |
| checkpoint-1000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-1000/trainer_state.json | Configuration | 55.6 KB | — |
| checkpoint-1500/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-1500/config.json | Configuration | 801 B | — |
| checkpoint-1500/generation_config.json | Configuration | 154 B | — |
| checkpoint-1500/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-1500/trainer_state.json | Configuration | 84.0 KB | — |
| checkpoint-2000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-2000/config.json | Configuration | 801 B | — |
| checkpoint-2000/generation_config.json | Configuration | 154 B | — |
| checkpoint-2000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-2000/trainer_state.json | Configuration | 112.5 KB | — |
| checkpoint-2500/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-2500/config.json | Configuration | 801 B | — |
| checkpoint-2500/generation_config.json | Configuration | 154 B | — |
| checkpoint-2500/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-2500/trainer_state.json | Configuration | 140.9 KB | — |
| checkpoint-3000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-3000/config.json | Configuration | 801 B | — |
| checkpoint-3000/generation_config.json | Configuration | 154 B | — |
| checkpoint-3000/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-3000/trainer_state.json | Configuration | 169.2 KB | — |
| checkpoint-3500/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-3500/config.json | Configuration | 801 B | — |
| checkpoint-3500/generation_config.json | Configuration | 154 B | — |
| checkpoint-3500/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-3500/trainer_state.json | Configuration | 197.7 KB | — |
| checkpoint-4000/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-4000/config.json | Configuration | 801 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 | 226.2 KB | — |
| checkpoint-4500/added_tokens.json | Configuration | 27.7 KB | — |
| checkpoint-4500/config.json | Configuration | 801 B | — |
| checkpoint-4500/generation_config.json | Configuration | 154 B | — |
| checkpoint-4500/special_tokens_map.json | Configuration | 22.6 KB | — |
| checkpoint-4500/trainer_state.json | Configuration | 254.6 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 | 28.2 KB | — |
| config.json | Configuration | 801 B | — |
| special_tokens_map.json | Configuration | 22.6 KB | — |
| README.md | Documentation | 2.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| checkpoint-1000/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-1000/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-1500/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-1500/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-2000/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-2000/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-2500/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-2500/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-3000/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-3000/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-3500/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-3500/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-4000/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-4000/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-4500/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-4500/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| checkpoint-500/spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| checkpoint-500/tokenizer_config.json | Tokenizer | 233.6 KB | — |
| spiece.model | Tokenizer | 1.1 MB | f98674a11db1 |
| tokenizer_config.json | Tokenizer | 233.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 782.0 MB
Download from Francesca Padovani
Released by Francesca Padovani through its official repository on Hugging Face.
Built From
- Derived from francesca9805/zho-hans-10mb-ppt-Dp-10mb-packed-bfdiso_seed3407
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 782.0 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 zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407
How much GPU memory does zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 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 zho-hans-10mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 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/hebhebr10mb. 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.