DynMoE Qwen 1.8B is an open-source language model by LINs-lab. Features: 3.4b LLM, VRAM: 5.7GB, Context: 8K, License: apache-2.0, MoE, LLM Explorer Score: 0.12.
| Model Type |
| |||||||||||||||||||
| Additional Notes |
| |||||||||||||||||||
| Training Details |
| |||||||||||||||||||
| Release Notes |
|
| LLM Name | DynMoE Qwen 1.8B |
| Repository 🤗 | https://huggingface.co/LINs-lab/DynMoE-Qwen-1.8B |
| Model Size | 3.4b |
| Required VRAM | 5.7 GB |
| Updated | 2026-08-05 |
| Maintainer | LINs-lab |
| Model Type | moe_llava_qwen |
| Model Files | |
| Model Architecture | LlavaQWenForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | QWenTokenizer |
| Padding Token | <|extra_0|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |