LLM Name | Sparsetral 16x7B V2 |
Repository ๐ค | https://huggingface.co/serpdotai/sparsetral-16x7B-v2 |
Model Size | 9.4b |
Required VRAM | 18.7 GB |
Updated | 2024-12-26 |
Maintainer | serpdotai |
Model Type | sparsetral |
Model Files | |
Supported Languages | en |
Model Architecture | modeling_sparsetral.MistralForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.37.2 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Sparsetral 16x7B V2 SPIN Iter1 | 32K / 18.7 GB | 21 | 13 |
Sparsetral 16x7B V2 SPIN Iter0 | 32K / 18.7 GB | 15 | 8 |
...s Sparsetral Mistral 16x7b MoE | 32K / 18.7 GB | 11 | 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