LLM Name | Qwen2 72B Instruct 8bit |
Repository ๐ค | https://huggingface.co/mlx-community/Qwen2-72B-Instruct-8bit |
Base Model(s) | |
Model Size | 72b |
Required VRAM | 77.1 GB |
Updated | 2024-09-07 |
Maintainer | mlx-community |
Model Type | qwen2 |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Quantization Type | 8bit |
Model Architecture | Qwen2ForCausalLM |
License | other |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.40.1 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
ECE ILAB Q1 | 32K / 77.8 GB | 2463 | 0 |
Qwen2 72B Instruct Bnb 4bit | 32K / 41.2 GB | 1115 | 6 |
Qwen2 72B Instruct 4bit | 32K / 40.9 GB | 48 | 2 |
...struct Mix Calibration 4B EXL2 | 32K / 38.8 GB | 4 | 2 |
Qwen2 72B Instruct Bpw5.5 EXL2 | 32K / 51.8 GB | 4 | 1 |
...n2 72B Instruct 4.0bpw H6 EXL2 | 32K / 38.6 GB | 12 | 1 |
Qwen2 72B Instruct Bpw4 EXL2 | 32K / 38.7 GB | 6 | 0 |
...n2 72B Instruct 3.5bpw H6 EXL2 | 32K / 34.3 GB | 7 | 2 |
...n2 72B Instruct 3.0bpw H6 EXL2 | 32K / 29.9 GB | 7 | 1 |
Qwen2 72B Instruct EXL2 8.0bpw | 32K / 65.6 GB | 5 | 1 |
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