LLM Name | Gemma 2 27B It FP8 |
Repository ๐ค | https://huggingface.co/nm-testing/gemma-2-27b-it-FP8 |
Model Size | 27b |
Required VRAM | 28.3 GB |
Updated | 2024-10-12 |
Maintainer | nm-testing |
Model Type | gemma2 |
Model Files | |
Model Architecture | Gemma2ForCausalLM |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.42.1 |
Tokenizer Class | GemmaTokenizer |
Padding Token | <pad> |
Vocabulary Size | 256000 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Gemma 2 27B It 8bit | 10 | 318 | 28 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Gemma 2 27B It | 8K / 54.7 GB | 148028 | 306 |
Datagemma Rag 27B It | 8K / 54.7 GB | 2191 | 163 |
Gemma 2 27B | 8K / 108.3 GB | 78658 | 126 |
Datagemma Rig 27B It | 8K / 54.7 GB | 1330 | 91 |
Gemma 2 27B It Abliterated | 8K / 54.7 GB | 2609 | 16 |
Magnum V3 27B Kto | 8K / 108.2 GB | 1708 | 9 |
Gemma2 Gutenberg 27B | 8K / 54.7 GB | 1815 | 4 |
Gemma 2 27B It SimPO 37K | 8K / 54.7 GB | 2142 | 16 |
Gemma 2 27B Chinese Chat | 8K / 54.7 GB | 2267 | 59 |
...ma 2 27B It SimPO 37K 100steps | 8K / 54.7 GB | 1467 | 9 |
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