LLM Name | Pearl 3x7B |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 18.5b |
Required VRAM | 37.1 GB |
Updated | 2024-07-26 |
Maintainer | louisbrulenaudet |
Model Type | mixtral |
Model Files | |
Supported Languages | en |
Model Architecture | MixtralForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.37.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <s> |
Vocabulary Size | 32002 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Lumina 3.5 | 0.3 | 32K / 37.1 GB | 2077 | 0 |
Topxtral 4x7B V0.1 | 0.3 | 32K / 37.1 GB | 4436 | 4 |
EastAsia 4x7B MoE Experiment | 0.3 | 32K / 37.1 GB | 921 | 1 |
Hyperion 3.0 Mixtral 3x7B | 0.2 | 32K / 37.1 GB | 308 | 4 |
Blitz AI MoE V0.7 | 0.2 | 32K / 37.1 GB | 313 | 1 |
Blitz AI MoE V0.4 | 0.2 | 32K / 37.1 GB | 303 | 1 |
HeroBophades 3x7B | 0.2 | 32K / 37.1 GB | 256 | 1 |
MoE 3x7b QA Code Inst | 0.2 | 32K / 37 GB | 313 | 4 |
Franken MoE 18B V0.1 | 0.2 | 32K / 37.1 GB | 320 | 2 |
Wizard Kun Lake 3x7B MoE | 0.2 | 32K / 37.1 GB | 6 | 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