This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Open-weight model · Text generation
cerulean-lab4-k1-964f796a
by Nathan Tung Nat1an/cerulean-lab4-k1-964f796a
cerulean-lab4-k1-964f796a is an open-weight model for text generation from Nathan Tung. It has 124M 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 is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
Parameters124M
Context—
Weights497.9 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve cerulean-lab4-k1-964f796a (124M 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 Oct 7, 2026.
cerulean-lab4-k1-964f796a on every accelerator the SAVRN Index prices, at every precision
Model Card
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Excerpt from the card by Nathan Tung.
Configuration
- Architecture
- GPT2LMHeadModel
- Vocabulary size
- 50,304
- Model type
- gpt2
Identity and Version
- Repository
- Nat1an/cerulean-lab4-k1-964f796a
- Publisher
- Nathan Tung
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 124M parameters
- Languages
- Not stated by the source
- Revision
- 0b11837a21131471266423deb964bdfac122ff63
- First published
- 2026-10-01
- Last updated
- 2026-10-01
Files and Weights
10 files, 502.7 MB in total. The weights are 1 file totalling 497.9 MB in safetensors.
Weights1 file · 497.9 MB
Configuration3 files · 1.5 KB
Tokenizer4 files · 4.8 MB
Documentation1 file · 5.2 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 497.9 MB | 0590638d6a3c |
| config.json | Configuration | 787 B | — |
| generation_config.json | Configuration | 176 B | — |
| special_tokens_map.json | Configuration | 583 B | — |
| README.md | Documentation | 5.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| merges.txt | Tokenizer | 456.3 KB | — |
| tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer_config.json | Tokenizer | 507 B | — |
| vocab.json | Tokenizer | 798.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 497.9 MB
Download from Nathan Tung
Released by Nathan Tung through its official repository on Hugging Face.
Built From
- Described by arXiv:1910.09700
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 497.9 MB |
| 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 cerulean-lab4-k1-964f796a
How much GPU memory does cerulean-lab4-k1-964f796a need?
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (124M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run cerulean-lab4-k1-964f796a 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 is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
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 is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This is the lab4-yoru-AY-482206 checkpoint, trained from scratch on English C4. It was selected by the lowest development loss among nine experimental recipes. The independent seed repeat and reserved audit evaluation were still pending when this checkpoint was published. Reported scores are local evaluation proxies, not an official online-judge result. - Stock Hugging Face GPT2LMHeadModel: 12 layers, 12 attention heads, hidden width 768, context length 1,024, vocabulary 50,257, tied input/output embeddings. - 124,439,808 unique parameters, commonly described as GPT-2 small. The lab uses the historical 117M model-family label. - GPT-2 tokenizer; documents packed with EOS separators. No…