LLM Name | Qwen2 72B Instruct GPTQ Int8 |
Repository | Open on ๐ค |
Model Size | 72b |
Required VRAM | 77 GB |
Updated | 2024-07-27 |
Maintainer | Qwen |
Model Type | qwen2 |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | Qwen2ForCausalLM |
License | other |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.37.0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Qwen2 72B Instruct GPTQ Int4 | 0.3 | 32K / 41.6 GB | 14496 | 24 |
ECE ILAB Q1 | 0.4 | 32K / 77.8 GB | 21 | 0 |
Qwen2 72B Instruct Bnb 4bit | 0.3 | 32K / 41.2 GB | 1969 | 6 |
Qwen2 72B Instruct 4bit | 0.2 | 32K / 40.9 GB | 47 | 2 |
...n2 72B Instruct 3.0bpw H6 EXL2 | 0.2 | 32K / 29.9 GB | 32 | 1 |
Qwen2 72B Instruct 8bit | 0.2 | 32K / 77.1 GB | 29 | 1 |
...n2 72B Instruct 3.5bpw H6 EXL2 | 0.2 | 32K / 34.3 GB | 16 | 2 |
...struct Mix Calibration 4B EXL2 | 0.2 | 32K / 38.8 GB | 11 | 2 |
...n2 72B Instruct 4.0bpw H6 EXL2 | 0.2 | 32K / 38.6 GB | 19 | 1 |
Qwen2 72B Instruct Bpw5.5 EXL2 | 0.2 | 32K / 51.8 GB | 6 | 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