Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text generation

SmolLM2-FT-MyDataset

by Roy Mazumder aritroroy0/SmolLM2-FT-MyDataset

SmolLM2-FT-MyDataset is an open-weight model for text generation from Roy Mazumder, released under Apache License 2.0. It has 135M parameters and a 8,192-token context. 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 HuggingFaceTB/SmolLM2-135M on an unknown dataset.

Parameters135M
Context8,192
Weights538.1 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve SmolLM2-FT-MyDataset (135M 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 0.3 GB 0.3 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.1 GB 0.2 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 18, 2026.

SmolLM2-FT-MyDataset on every accelerator the SAVRN Index prices, at every precision

Model Card

By Roy Mazumder, published under apache-2.0, revision 27a2b887f0dd.

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M 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 - lrschedulertype: linear - trainingsteps: 1000 - Transformers 4.46.3 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.20.3

Read Roy Mazumder's full model card

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0215

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss
1.0657 0.0885 50 1.1590
1.1116 0.1770 100 1.1241
1.0624 0.2655 150 1.0955
1.0482 0.3540 200 1.0797
1.0412 0.4425 250 1.0705
1.0292 0.5310 300 1.0615
1.0034 0.6195 350 1.0548
1.0065 0.7080 400 1.0508
1.0211 0.7965 450 1.0426
1.0762 0.8850 500 1.0337
0.9907 0.9735 550 1.0283
0.8018 1.0619 600 1.0331
0.812 1.1504 650 1.0299
0.7538 1.2389 700 1.0311
0.8559 1.3274 750 1.0285
0.8103 1.4159 800 1.0249
0.7769 1.5044 850 1.0253
0.8237 1.5929 900 1.0228
0.8623 1.6814 950 1.0217
0.7915 1.7699 1000 1.0215

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.11.0+cu130
  • Datasets 4.8.5
  • Tokenizers 0.20.3

Configuration

Architecture
LlamaForCausalLM
Context length (tokens)
8,192
Layers
30
Hidden size
576
Feed-forward size
1,536
Attention heads
9
Key/value heads
3
Head dimension
64
Vocabulary size
49,152
RoPE base
100,000
Stored precision
float32
Model type
llama

Identity and Version

Repository
aritroroy0/SmolLM2-FT-MyDataset
Publisher
Roy Mazumder
Task
Text generation
Modality
Text
Library
transformers
Parameters
135M parameters
Languages
trl, sft
Revision
27a2b887f0ddedf0c592f46186d0a372389ca27c
First published
2026-10-16
Last updated
2026-10-16

Files and Weights

11 files, 542.9 MB in total. The weights are 2 files totalling 538.1 MB in bin, safetensors.

Weights2 files · 538.1 MB
Configuration3 files · 1.5 KB
Tokenizer4 files · 4.8 MB
Documentation1 file · 2.5 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights538.1 MB cc3e9dceb21a
training_args.binWeights5.9 KB 8e0c3f63d372
config.jsonConfiguration812 B —
generation_config.jsonConfiguration132 B —
special_tokens_map.jsonConfiguration565 B —
README.mdDocumentation2.5 KB —
.gitattributesRepository1.5 KB —
merges.txtTokenizer466.4 KB —
tokenizer.jsonTokenizer3.5 MB —
tokenizer_config.jsonTokenizer3.6 KB —
vocab.jsonTokenizer800.7 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
538.1 MB
Download from Roy Mazumder

Released by Roy Mazumder through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published538.1 MB
16-bit0.3 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 SmolLM2-FT-MyDataset

How much GPU memory does SmolLM2-FT-MyDataset need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (135M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run SmolLM2-FT-MyDataset 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.

Can I use SmolLM2-FT-MyDataset commercially?

Yes. SmolLM2-FT-MyDataset is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is SmolLM2-FT-MyDataset's context length?

8,192 tokens, from the maximum position embeddings in its published configuration.

Similar Models

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…

Open weights apache-2.0 135M parameters 8,192 tokens transformers
View model

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…

Open weights apache-2.0 135M parameters 8,192 tokens transformers
View model

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct on an unknown dataset. The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 1 - evalbatchsize: 1 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 4 - lrschedulertype: linear - numepochs: 1 - Transformers 5.17.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2

Open weights apache-2.0 135M parameters 8,192 tokens transformers
View model

Model · Text generation

Smol-GPT-Fp8

Gggff123

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 135M parameters 8,192 tokens transformers
View model

Model · Text generation

Smol-GPT-RAW

Gggff123

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 135M parameters 8,192 tokens transformers
View model

Model · Text generation

gpt2

OpenAI community

Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in and first released at this page. model. Content from this model card has been written by the Hugging Face team to complete the information they provided and give specific examples of bias. GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs…

Open weights mit 137M parameters transformers
View model