SAVRN
Search Contact SAVRN

Open-weight model · Text generation

rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407

by Francesca Padovani francesca9805/rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407

rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 is an open-weight model for text generation from Francesca Padovani. It has 125M parameters. At 16-bit it needs about 0.3 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/rus-cyrl-100mb-ppt-Dp-10mb-packed-bfdisoseed3407. It has been trained using TRL. This model was trained with SFT.

Parameters125M
Context—
Weights6.0 GB
License—
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 (125M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso 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 Oct 7, 2026.

rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 on every accelerator the SAVRN Index prices, at every precision

Model Card

This model is a fine-tuned version of francesca9805/rus-cyrl-100mb-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/rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407
Publisher
Francesca Padovani
Task
Text generation
Modality
Text
Library
transformers
Parameters
125M parameters
Languages
sft, trl
Revision
5888bedc208d629d05f7d226e49027153a4ca898
First published
2026-10-03
Last updated
2026-10-03

Files and Weights

240 files, 6.0 GB in total. The weights are 71 files totalling 6.0 GB in bin, pth, safetensors.

Weights71 files · 6.0 GB
Configuration119 files · 9.0 MB
Tokenizer48 files · 41.9 MB
Documentation1 file · 2.0 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
checkpoint-1000/model.safetensorsWeights249.6 MB f244e7317938
checkpoint-1000/rng_state.pthWeights14.6 KB 6d1037033e96
checkpoint-1000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-10000/model.safetensorsWeights249.6 MB e99a2468950f
checkpoint-10000/rng_state.pthWeights14.6 KB 8afa0b7ac8ec
checkpoint-10000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-10500/model.safetensorsWeights249.6 MB 1d408ad60aa8
checkpoint-10500/rng_state.pthWeights14.6 KB 8e85434e3bc0
checkpoint-10500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-11000/model.safetensorsWeights249.6 MB 601f8fedbf9c
checkpoint-11000/rng_state.pthWeights14.6 KB 876982dc096f
checkpoint-11000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-11260/model.safetensorsWeights249.6 MB 547ad93513f4
checkpoint-11260/rng_state.pthWeights14.6 KB 12eba6e6dac6
checkpoint-11260/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-1500/model.safetensorsWeights249.6 MB 912a83c43040
checkpoint-1500/rng_state.pthWeights14.6 KB 9725e9838df4
checkpoint-1500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-2000/model.safetensorsWeights249.6 MB a5f994c00492
checkpoint-2000/rng_state.pthWeights14.6 KB 43d0be2599fc
checkpoint-2000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-2500/model.safetensorsWeights249.6 MB ae7e6f0a66a3
checkpoint-2500/rng_state.pthWeights14.6 KB 43761cffeade
checkpoint-2500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-3000/model.safetensorsWeights249.6 MB c6b45c941db5
checkpoint-3000/rng_state.pthWeights14.6 KB 4b4d4c4f3075
checkpoint-3000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-3500/model.safetensorsWeights249.6 MB ec946c1317eb
checkpoint-3500/rng_state.pthWeights14.6 KB 985da7653fcf
checkpoint-3500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-4000/model.safetensorsWeights249.6 MB 07b271710f80
checkpoint-4000/rng_state.pthWeights14.6 KB 081d3b110934
checkpoint-4000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-4500/model.safetensorsWeights249.6 MB 64d3ce9cdbf8
checkpoint-4500/rng_state.pthWeights14.6 KB 87c597a2e7e9
checkpoint-4500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-500/model.safetensorsWeights249.6 MB 456e271c2b74
checkpoint-500/rng_state.pthWeights14.6 KB 3282c4a44818
checkpoint-500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-5000/model.safetensorsWeights249.6 MB 1dca83ca71e6
checkpoint-5000/rng_state.pthWeights14.6 KB becc96cffd7e
checkpoint-5000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-5500/model.safetensorsWeights249.6 MB e9c440b3cb54
checkpoint-5500/rng_state.pthWeights14.6 KB 16e4802b398f
checkpoint-5500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-6000/model.safetensorsWeights249.6 MB eec99b04b36e
checkpoint-6000/rng_state.pthWeights14.6 KB 63195e8f2144
checkpoint-6000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-6500/model.safetensorsWeights249.6 MB 820ca7cc6a1c
checkpoint-6500/rng_state.pthWeights14.6 KB 6b91e1a928fd
checkpoint-6500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-7000/model.safetensorsWeights249.6 MB 72c27275a689
checkpoint-7000/rng_state.pthWeights14.6 KB fc4183a866d9
checkpoint-7000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-7500/model.safetensorsWeights249.6 MB 1ec79d015614
checkpoint-7500/rng_state.pthWeights14.6 KB 717c74e46bcf
checkpoint-7500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-8000/model.safetensorsWeights249.6 MB ec34bb0bb433
checkpoint-8000/rng_state.pthWeights14.6 KB 2e7152f25ca5
checkpoint-8000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-8500/model.safetensorsWeights249.6 MB cc49382f2bd9
checkpoint-8500/rng_state.pthWeights14.6 KB f02b7a0e2505
checkpoint-8500/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-9000/model.safetensorsWeights249.6 MB 7dd4a4c2269f
checkpoint-9000/rng_state.pthWeights14.6 KB 1fbaaf5966cb
checkpoint-9000/training_args.binWeights6.4 KB 53a046587ebd
checkpoint-9500/model.safetensorsWeights249.6 MB 4c9616661d08
checkpoint-9500/rng_state.pthWeights14.6 KB bad593e6def5
checkpoint-9500/training_args.binWeights6.4 KB 53a046587ebd
model.safetensorsWeights249.6 MB 547ad93513f4
training_args.binWeights6.4 KB 53a046587ebd
added_tokens.jsonConfiguration27.7 KB —
checkpoint-1000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-1000/config.jsonConfiguration803 B —
checkpoint-1000/generation_config.jsonConfiguration154 B —
checkpoint-1000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-1000/trainer_state.jsonConfiguration55.5 KB —
checkpoint-10000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-10000/config.jsonConfiguration803 B —
checkpoint-10000/generation_config.jsonConfiguration154 B —
checkpoint-10000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-10000/trainer_state.jsonConfiguration567.0 KB —
checkpoint-10500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-10500/config.jsonConfiguration803 B —
checkpoint-10500/generation_config.jsonConfiguration154 B —
checkpoint-10500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-10500/trainer_state.jsonConfiguration595.4 KB —
checkpoint-11000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-11000/config.jsonConfiguration803 B —
checkpoint-11000/generation_config.jsonConfiguration154 B —
checkpoint-11000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-11000/trainer_state.jsonConfiguration623.9 KB —
checkpoint-11260/added_tokens.jsonConfiguration27.7 KB —
checkpoint-11260/config.jsonConfiguration803 B —
checkpoint-11260/generation_config.jsonConfiguration154 B —
checkpoint-11260/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-11260/trainer_state.jsonConfiguration638.5 KB —
checkpoint-1500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-1500/config.jsonConfiguration803 B —
checkpoint-1500/generation_config.jsonConfiguration154 B —
checkpoint-1500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-1500/trainer_state.jsonConfiguration83.9 KB —
checkpoint-2000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-2000/config.jsonConfiguration803 B —
checkpoint-2000/generation_config.jsonConfiguration154 B —
checkpoint-2000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-2000/trainer_state.jsonConfiguration112.3 KB —
checkpoint-2500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-2500/config.jsonConfiguration803 B —
checkpoint-2500/generation_config.jsonConfiguration154 B —
checkpoint-2500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-2500/trainer_state.jsonConfiguration140.7 KB —
checkpoint-3000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-3000/config.jsonConfiguration803 B —
checkpoint-3000/generation_config.jsonConfiguration154 B —
checkpoint-3000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-3000/trainer_state.jsonConfiguration169.1 KB —
checkpoint-3500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-3500/config.jsonConfiguration803 B —
checkpoint-3500/generation_config.jsonConfiguration154 B —
checkpoint-3500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-3500/trainer_state.jsonConfiguration197.5 KB —
checkpoint-4000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-4000/config.jsonConfiguration803 B —
checkpoint-4000/generation_config.jsonConfiguration154 B —
checkpoint-4000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-4000/trainer_state.jsonConfiguration225.8 KB —
checkpoint-4500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-4500/config.jsonConfiguration803 B —
checkpoint-4500/generation_config.jsonConfiguration154 B —
checkpoint-4500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-4500/trainer_state.jsonConfiguration254.2 KB —
checkpoint-500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-500/config.jsonConfiguration803 B —
checkpoint-500/generation_config.jsonConfiguration154 B —
checkpoint-500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-500/trainer_state.jsonConfiguration28.2 KB —
checkpoint-5000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-5000/config.jsonConfiguration803 B —
checkpoint-5000/generation_config.jsonConfiguration154 B —
checkpoint-5000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-5000/trainer_state.jsonConfiguration282.6 KB —
checkpoint-5500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-5500/config.jsonConfiguration803 B —
checkpoint-5500/generation_config.jsonConfiguration154 B —
checkpoint-5500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-5500/trainer_state.jsonConfiguration311.1 KB —
checkpoint-6000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-6000/config.jsonConfiguration803 B —
checkpoint-6000/generation_config.jsonConfiguration154 B —
checkpoint-6000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-6000/trainer_state.jsonConfiguration339.5 KB —
checkpoint-6500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-6500/config.jsonConfiguration803 B —
checkpoint-6500/generation_config.jsonConfiguration154 B —
checkpoint-6500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-6500/trainer_state.jsonConfiguration367.9 KB —
checkpoint-7000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-7000/config.jsonConfiguration803 B —
checkpoint-7000/generation_config.jsonConfiguration154 B —
checkpoint-7000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-7000/trainer_state.jsonConfiguration396.4 KB —
checkpoint-7500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-7500/config.jsonConfiguration803 B —
checkpoint-7500/generation_config.jsonConfiguration154 B —
checkpoint-7500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-7500/trainer_state.jsonConfiguration424.9 KB —
checkpoint-8000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-8000/config.jsonConfiguration803 B —
checkpoint-8000/generation_config.jsonConfiguration154 B —
checkpoint-8000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-8000/trainer_state.jsonConfiguration453.3 KB —
checkpoint-8500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-8500/config.jsonConfiguration803 B —
checkpoint-8500/generation_config.jsonConfiguration154 B —
checkpoint-8500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-8500/trainer_state.jsonConfiguration481.8 KB —
checkpoint-9000/added_tokens.jsonConfiguration27.7 KB —
checkpoint-9000/config.jsonConfiguration803 B —
checkpoint-9000/generation_config.jsonConfiguration154 B —
checkpoint-9000/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-9000/trainer_state.jsonConfiguration510.2 KB —
checkpoint-9500/added_tokens.jsonConfiguration27.7 KB —
checkpoint-9500/config.jsonConfiguration803 B —
checkpoint-9500/generation_config.jsonConfiguration154 B —
checkpoint-9500/special_tokens_map.jsonConfiguration22.6 KB —
checkpoint-9500/trainer_state.jsonConfiguration538.6 KB —
config.jsonConfiguration803 B —
generation_config.jsonConfiguration154 B —
special_tokens_map.jsonConfiguration22.6 KB —
README.mdDocumentation2.0 KB —
.gitattributesRepository1.5 KB —
checkpoint-1000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-1000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-10000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-10000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-10500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-10500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-11000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-11000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-11260/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-11260/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-1500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-1500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-2000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-2000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-2500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-2500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-3000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-3000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-3500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-3500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-4000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-4000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-4500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-4500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-5000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-5000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-5500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-5500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-6000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-6000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-6500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-6500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-7000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-7000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-7500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-7500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-8000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-8000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-8500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-8500/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-9000/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-9000/tokenizer_config.jsonTokenizer233.6 KB —
checkpoint-9500/spiece.modelTokenizer1.5 MB 76cd09e76cf6
checkpoint-9500/tokenizer_config.jsonTokenizer233.6 KB —
spiece.modelTokenizer1.5 MB 76cd09e76cf6
tokenizer_config.jsonTokenizer233.6 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
6.0 GB
Download from Francesca Padovani

Released by Francesca Padovani through its official repository on Hugging Face.

Built From

  • Derived from francesca9805/rus-cyrl-100mb-ppt-Dp-10mb-packed-bfdiso_seed3407

Memory Requirements

PrecisionWeights in memory
As published6.0 GB
16-bit0.2 GB
8-bit0.1 GB
4-bit0.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407

How much GPU memory does rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407 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 rus-cyrl-100mb-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