LLM Name | Qwen1.5 72B Chat GPTQ Int4 |
Repository | Open on ๐ค |
Model Size | 72b |
Required VRAM | 41.3 GB |
Updated | 2024-07-27 |
Maintainer | Qwen |
Model Type | qwen2 |
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 |
Qwen2 72B Instruct GPTQ Int8 | 0.3 | 32K / 77 GB | 7137 | 12 |
Qwen1.5 72B Chat GPTQ | 0.2 | 32K / 45.4 GB | 10 | 2 |
Qwen1.5 72B Chat GPTQ Int8 | 0.2 | 32K / 77 GB | 53 | 6 |
Qwen2 72B Bnb 4bit | 0.3 | 128K / 41.2 GB | 820 | 3 |
...in 2.9.2 Qwen2 72B 6.0bpw EXL2 | 0.2 | 128K / 56.1 GB | 18 | 1 |
...Qwen2 72B 4 0bpw H6 EXL2 Pippa | 0.2 | 128K / 38.6 GB | 18 | 1 |
...phin 292 Qwen2 72b EXL2 4 0bpw | 0.2 | 128K / 38.6 GB | 15 | 1 |
...n 2.9.2 Qwen72b 8.0bpw H8 EXL2 | 0.2 | 128K / 66.8 GB | 6 | 2 |
Qwen2 72B 4bit | 0.2 | 128K / 40.9 GB | 12 | 0 |
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