Model Type |
| |
Additional Notes |
|
LLM Name | Gemma 1.1 7B It 4bit |
Repository ๐ค | https://huggingface.co/mlx-community/gemma-1.1-7b-it-4bit |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 5.9โฏGB |
Updated | 2024-12-29 |
Maintainer | mlx-community |
Model Type | gemma |
Model Files | |
Quantization Type | 4bit |
Model Architecture | GemmaForCausalLM |
License | gemma |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.39.3 |
Padding Token | <pad> |
Vocabulary Size | 256000 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...t Cleaner Gemma 32k Merged 16b | 31K / 17.1โGB | 21 | 0 |
...ruct Malayalam Model Vllm 4bit | 16K / 5.6โGB | 18 | 0 |
... Codegemma 2 7B It Alpaca V1.2 | 8K / 17.1โGB | 18 | 0 |
Codegemma 7B It 8bit | 8K / 9.5โGB | 323 | 4 |
Gemma 7B Bnb 4bit | 8K / 5.6โGB | 3378 | 17 |
Fbt Gemma 7B | 8K / 17.1โGB | 16 | 0 |
Codegemma 7B It 4bit | 8K / 5.9โGB | 41 | 1 |
Codegemma 7B 4bit | 8K / 5.9โGB | 20 | 0 |
Swahili Gemma | 8K / 17.1โGB | 43 | 1 |
Gemma 1.1 7B It 4bit | 8K / 5.9โGB | 16 | 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