LLM Name | Qwen Qwen2 72B FP8 Dynamic |
Repository ๐ค | https://huggingface.co/Model-SafeTensors/Qwen-Qwen2-72B-FP8-Dynamic |
Model Size | 72b |
Required VRAM | 75.5 GB |
Updated | 2025-02-19 |
Maintainer | Model-SafeTensors |
Model Type | qwen2 |
Model Files | |
Model Architecture | Qwen2ForCausalLM |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.38.1 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Ultiima 72B | 128K / 146.1 GB | 2227 | 1 |
EVA Qwen2.5 72B V0.2 | 128K / 146 GB | 2621 | 16 |
Qwen2.5 72B | 128K / 145.5 GB | 27240 | 58 |
AceInstruct 72B | 128K / 146 GB | 184 | 14 |
Ultiima 72B V1.5 | 128K / 146.1 GB | 110 | 0 |
Homer V1.0 Qwen2.5 72B | 128K / 146.1 GB | 146 | 6 |
Qwen2 72B | 128K / 145.5 GB | 11520 | 197 |
Dolphin 2.9.2 Qwen2 72B | 128K / 146 GB | 8109 | 154 |
...n2.5 72B 2x Instruct TIES V1.0 | 128K / 146.1 GB | 6 | 0 |
Calme 2.3 Qwen2 72B | 128K / 146 GB | 2168 | 2 |
๐ 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! ๐