Qwen1.5 MoE A2.7B 20 Experts is an open-source language model by Na0s. Features: 5.2b LLM, VRAM: 20.7GB, Context: 8K, MoE, LLM Explorer Score: 0.16.
| 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 |