Arxiv:1910.09700 Autotrain compatible Base model:finetune:qwen/qwen1... Base model:qwen/qwen1.5-moe-a2... Conversational En Endpoints compatible Moe Qwen2 moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Na0s/Qwen1.5-MoE-A2.7B-20-experts
Qwen1.5 MoE A2.7B 20 Experts 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)
Qwen1.5 MoE A2.7B 20 Experts Parameters and Internals
| LLM Name | Qwen1.5 MoE A2.7B 20 Experts |
| Repository 🤗 | https://huggingface.co/Na0s/Qwen1.5-MoE-A2.7B-20-experts |
| Base Model(s) | |
| Model Size | 5.2b |
| Required VRAM | 20.7 GB |
| Updated | 2024-12-15 |
| Maintainer | Na0s |
| Model Type | qwen2_moe |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2MoeForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.45.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Rank the Qwen1.5 MoE A2.7B 20 Experts 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? 51566 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124