Open-weight model
medical-bidirectional-machine-translation-checkpoints-170348
by NGUYEN DUC HIEU ndhieu1101/medical-bidirectional-machine-translation-checkpoints-170348
medical-bidirectional-machine-translation-checkpoints-170348 is an open-weight model from NGUYEN DUC HIEU. It has 275M parameters. At 16-bit it needs about 0.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve medical-bidirectional-machine-translation-checkpoints-170348 (275M 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 | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.2 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.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 50,048
- Model type
- t5
Identity and Version
- Repository
- ndhieu1101/medical-bidirectional-machine-translation-checkpoints-170348
- Publisher
- NGUYEN DUC HIEU
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 275M parameters
- Languages
- Not stated by the source
- Revision
- c66f1bfe5a6b4ebf6320ab571789a7161c7512ad
- First published
- 2026-09-20
- Last updated
- 2026-09-21
Files and Weights
35 files, 7.7 GB in total. The weights are 14 files totalling 7.7 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-10000/model.safetensors | Weights | 1.1 GB | 1e7639891cdc |
| checkpoint-10000/optimizer.pt | Weights | 2.2 GB | fcdcfea94468 |
| checkpoint-10000/rng_state.pth | Weights | 14.6 KB | 6c1901214a8d |
| checkpoint-10000/scaler.pt | Weights | 1.4 KB | 1e6fd97f105f |
| checkpoint-10000/scheduler.pt | Weights | 1.5 KB | 47eb0aac4200 |
| checkpoint-10000/training_args.bin | Weights | 6.0 KB | 58ca93c2c6d7 |
| checkpoint-5000/model.safetensors | Weights | 1.1 GB | bf66c33c4071 |
| checkpoint-5000/optimizer.pt | Weights | 2.2 GB | af327ae986a6 |
| checkpoint-5000/rng_state.pth | Weights | 14.6 KB | 1bc8a41296a3 |
| checkpoint-5000/scaler.pt | Weights | 1.4 KB | 82ad8990572a |
| checkpoint-5000/scheduler.pt | Weights | 1.5 KB | 3cd20009a32e |
| checkpoint-5000/training_args.bin | Weights | 6.0 KB | 58ca93c2c6d7 |
| model.safetensors | Weights | 1.1 GB | 1e7639891cdc |
| training_args.bin | Weights | 6.0 KB | 58ca93c2c6d7 |
| added_tokens.json | Configuration | 2.6 KB | — |
| checkpoint-10000/added_tokens.json | Configuration | 2.6 KB | — |
| checkpoint-10000/config.json | Configuration | 744 B | — |
| checkpoint-10000/generation_config.json | Configuration | 122 B | — |
| checkpoint-10000/special_tokens_map.json | Configuration | 2.5 KB | — |
| checkpoint-10000/trainer_state.json | Configuration | 18.9 KB | — |
| checkpoint-5000/added_tokens.json | Configuration | 2.6 KB | — |
| checkpoint-5000/config.json | Configuration | 744 B | — |
| checkpoint-5000/generation_config.json | Configuration | 122 B | — |
| checkpoint-5000/special_tokens_map.json | Configuration | 2.5 KB | — |
| checkpoint-5000/trainer_state.json | Configuration | 9.8 KB | — |
| config.json | Configuration | 744 B | — |
| generation_config.json | Configuration | 122 B | — |
| special_tokens_map.json | Configuration | 2.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| checkpoint-10000/spiece.model | Tokenizer | 1.1 MB | 3b4eda923bba |
| checkpoint-10000/tokenizer_config.json | Tokenizer | 20.7 KB | — |
| checkpoint-5000/spiece.model | Tokenizer | 1.1 MB | 3b4eda923bba |
| checkpoint-5000/tokenizer_config.json | Tokenizer | 20.7 KB | — |
| spiece.model | Tokenizer | 1.1 MB | 3b4eda923bba |
| tokenizer_config.json | Tokenizer | 20.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 7.7 GB
Released by NGUYEN DUC HIEU through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 7.7 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About medical-bidirectional-machine-translation-checkpoints-170348
How much GPU memory does medical-bidirectional-machine-translation-checkpoints-170348 need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (275M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run medical-bidirectional-machine-translation-checkpoints-170348 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.