asym_lora_nllb-iwslt2015 is an open-weight model from Đặng Hoàng Kiệt. Its published files total 42.3 MB.
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.
Model Card
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). - PEFT 0.20.0
Excerpt from the card by Đặng Hoàng Kiệt.
Identity and Version
- Repository
- AIOKiet/asym_lora_nllb-iwslt2015
- Publisher
- Đặng Hoàng Kiệt
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- c3b91d81b23f4e29578104e54da68638fa0ee346
- First published
- 2026-09-27
- Last updated
- 2026-09-27
Files and Weights
14 files, 42.3 MB in total. The weights are 2 files totalling 4.7 MB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 4.7 MB | 24b97fa58094 |
| training_args.bin | Weights | 6.0 KB | 52c4a4f043e8 |
| adapter_config.json | Configuration | 6.1 KB | — |
| results/asym_lora_training_history.json | Configuration | 12.8 KB | — |
| special_tokens_map.json | Configuration | 4.2 KB | — |
| README.md | Documentation | 5.2 KB | — |
| figures/loss_curve.pdf | Other | 11.1 KB | — |
| figures/loss_curve.png | Other | 254.1 KB | 0821c30fdff8 |
| figures/validation_metrics.pdf | Other | 12.1 KB | — |
| figures/validation_metrics.png | Other | 162.6 KB | cc7b9ce7b72b |
| sentencepiece.bpe.model | Other | 4.9 MB | 14bb8dfb35c0 |
| .gitattributes | Repository | 1.7 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | 43dabf690bcf |
| tokenizer_config.json | Tokenizer | 39.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.7 MB
Released by Đặng Hoàng Kiệt through its official repository on Hugging Face.
Built From
- Adapter of facebook/nllb-200-distilled-600M
- Derived from facebook/nllb-200-distilled-600M
- Described by arXiv:1910.09700
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.7 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.