LLM Name | Poro 34B AWQ |
Repository ๐ค | https://huggingface.co/gradjitta/Poro-34B-AWQ |
Model Size | 34b |
Required VRAM | 21 GB |
Updated | 2024-09-07 |
Maintainer | gradjitta |
Model Type | bloom |
Model Files | |
AWQ Quantization | Yes |
Quantization Type | awq |
Model Architecture | BloomForCausalLM |
License | apache-2.0 |
Transformers Version | 4.35.1 |
Tokenizer Class | BloomTokenizer |
Padding Token | <pad> |
Vocabulary Size | 128000 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Poro 34B AWQ | 0K / 21 GB | 30 | 2 |
Poro 34B Chat | 0K / 68 GB | 834 | 9 |
Poro 34B GPTQ | 0K / 20.3 GB | 40 | 3 |
Poro 34B | 0K / 68 GB | 1726 | 112 |
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