qwen2-hl3 is an open-weight model from SE, released under Apache License 2.0. It has 512-token context. Its published files total 21.8 KB.
Model Card
By SE, published under apache-2.0, revision 1ce11e7ba15d.
Read SE's full model card
tiny demo
Configuration
- Architecture
- HlModel
- Context length (tokens)
- 512
- Layers
- 2
- Hidden size
- 64
- Feed-forward size
- 128
- Attention heads
- 4
- Key/value heads
- 2
- Vocabulary size
- 1,024
- RoPE base
- 10000
- Stored precision
- float32
- Model type
- qwen2
Identity and Version
- Repository
- MONIADF-2/qwen2-hl3
- Publisher
- SE
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 1ce11e7ba15dcc5546b8b44c2a91d8ebbe3a5a98
- First published
- 2026-10-17
- Last updated
- 2026-10-17
Files and Weights
8 files, 21.8 KB in total. The weights are 1 file totalling 42 B in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 42 B | c052d0175b3e |
| config.json | Configuration | 481 B | — |
| modeling_hl.py | Configuration | 18.5 KB | — |
| README.md | Documentation | 40 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| .ms_upload_cache | Repository | 1.1 KB | — |
| tokenizer.json | Tokenizer | 91 B | — |
| tokenizer_config.json | Tokenizer | 71 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 42 B
Released by SE through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 42 B |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About qwen2-hl3
Can I use qwen2-hl3 commercially?
Yes. qwen2-hl3 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 qwen2-hl3's context length?
512 tokens, from the maximum position embeddings in its published configuration.