LLM Name | Magnum V2 123B Fp8 Dynamic |
Repository ๐ค | https://huggingface.co/leafspark/magnum-v2-123b-fp8-dynamic |
Base Model(s) | |
Model Size | 123b |
Required VRAM | 123.6 GB |
Updated | 2024-09-20 |
Maintainer | leafspark |
Model Type | mistral |
Model Files | |
Supported Languages | en fr de es it pt ru zh ja |
Model Architecture | MistralForCausalLM |
License | other |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.44.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 32768 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Magnum V2 123B | 128K / 207.6 GB | 1772 | 53 |
Lumimaid V0.2 123B | 128K / 217.2 GB | 2461 | 30 |
Luminum V0.1 123B | 128K / 211.9 GB | 342 | 13 |
Tess 3 Mistral Large 2 123B | 128K / 217.2 GB | 121 | 16 |
...minum V0.1 123B EXL2 2.7bpw H6 | 128K / 42.3 GB | 45 | 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