Arxiv:2405.14297 Autotrain compatible Custom code Endpoints compatible Image-text-to-text Moe Moe llava qwen Pytorch Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LINs-lab/DynMoE-Qwen-1.8B
DynMoE Qwen 1.8B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
DynMoE Qwen 1.8B Parameters and Internals
| 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 | 2025-02-22 |
| 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 |
Rank the DynMoE Qwen 1.8B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227