Model Type |
| ||||||||||||
Use Cases |
| ||||||||||||
Additional Notes |
| ||||||||||||
Supported Languages |
| ||||||||||||
Training Details |
| ||||||||||||
Input Output |
|
LLM Name | Ao Karasu 72B AWQ 4bit |
Repository ๐ค | https://huggingface.co/lightblue/ao-karasu-72B-AWQ-4bit |
Merged Model | Yes |
Model Size | 72b |
Required VRAM | 41.3 GB |
Updated | 2025-06-10 |
Maintainer | lightblue |
Model Type | qwen2 |
Model Files | |
AWQ Quantization | Yes |
Quantization Type | awq|4bit |
Model Architecture | Qwen2ForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.39.0.dev0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Tess V2.5.2 Qwen2 72B AWQ | 128K / 41.6 GB | 12 | 0 |
Qwen2.5 72B Instruct AWQ | 32K / 41.6 GB | 99918 | 68 |
Athene V2 Chat AWQ | 32K / 41.6 GB | 17 | 4 |
Qwen2 72B Instruct AWQ | 32K / 41.6 GB | 882 | 40 |
Qwen1.5 72B Chat AWQ | 32K / 41.3 GB | 2310 | 24 |
Qwen2 72B Instruct AWQ GEMM | 32K / 41.6 GB | 13 | 0 |
Qwen1.5 72B AWQ | 32K / 41.3 GB | 14 | 1 |
Typhoon V1.5 72B Instruct AWQ | 32K / 41.3 GB | 39 | 3 |
Liberated Qwen1.5 72B AWQ | 32K / 41.3 GB | 82 | 1 |
Qwen2 72B Bnb 4bit | 128K / 41.2 GB | 1443 | 4 |
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