LLM Name | MergedExpert 2x8b |
Repository ๐ค | https://huggingface.co/bhavnah/MergedExpert-2x8b |
Model Size | 12.9b |
Required VRAM | 25.8 GB |
Updated | 2024-09-07 |
Maintainer | bhavnah |
Model Type | mixtral |
Instruction-Based | Yes |
Model Files | |
Model Architecture | MixtralForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.41.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <s> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
MergedExperts 2x8b | 32K / 25.8 GB | 5 | 0 |
Megatron V3 2x7B | 32K / 25.8 GB | 61 | 3 |
NearalMistral 2x7B | 32K / 25.8 GB | 57 | 0 |
MistarlingMaid 2x7B Base | 32K / 25.8 GB | 63 | 0 |
...afted Hermetic Platypus C 2x7B | 32K / 25.8 GB | 57 | 0 |
...tral 7B Instruct V0.2 2x7B MoE | 32K / 25.8 GB | 1131 | 4 |
Orthogonal 2x7B Base | 32K / 25.8 GB | 651 | 0 |
Mistral 2x7b V0.1 | 32K / 25.8 GB | 6 | 1 |
Mistral Math 2x7b Mix | 32K / 25.8 GB | 62 | 4 |
...tral Instruct MoE Experimental | 32K / 25.8 GB | 62 | 2 |
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