bge_m3_onnx is an open-weight model from Run.. It has 8,194-token context. Its published files total 2.3 GB.
Parameters—
Context8,194
Weights2.2 MB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- XLMRobertaModel
- Context length (tokens)
- 8,194
- Layers
- 24
- Hidden size
- 1,024
- Feed-forward size
- 4,096
- Attention heads
- 16
- Vocabulary size
- 250,002
- Model type
- xlm-roberta
Identity and Version
- Repository
- harinsk8/bge_m3_onnx
- Publisher
- Run.
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- xlm-roberta
- Revision
- d31b36f057ab5e39efa9ffda46e5d6167709cc8f
- First published
- 2026-10-05
- Last updated
- 2026-10-05
Files and Weights
11 files, 2.3 GB in total. The weights are 3 files totalling 2.2 MB in onnx, pt.
Weights3 files · 2.2 MB
Configuration3 files · 2.8 KB
Tokenizer2 files · 17.1 MB
Other2 files · 2.3 GB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| colbert_linear.pt | Weights | 2.1 MB | 19bfbae397c2 |
| model.onnx | Weights | 97.8 KB | 9a261d935e3e |
| sparse_linear.pt | Weights | 3.5 KB | 45c93804d214 |
| config.json | Configuration | 673 B | — |
| ort_config.json | Configuration | 1.2 KB | — |
| special_tokens_map.json | Configuration | 964 B | — |
| model.onnx.data | Other | 2.3 GB | 89c101f1180c |
| sentencepiece.bpe.model | Other | 5.1 MB | cfc8146abe2a |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | 249df0778f23 |
| tokenizer_config.json | Tokenizer | 1.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.2 MB
Download from Run.
Released by Run. through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.2 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About bge_m3_onnx
What is bge_m3_onnx's context length?
8,194 tokens, from the maximum position embeddings in its published configuration.