LLM Name | Manticore 30B Chat Pyg Alpha Landmark |
Repository | Open on ๐ค |
Model Size | 30b |
Required VRAM | 65.2 GB |
Updated | 2024-07-27 |
Maintainer | Honkware |
Model Type | llama |
Model Files | |
Model Architecture | LlamaForCausalLM |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.30.2 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 32002 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Flash Llama 30M 20001 | 0.2 | 32K / 0.1 GB | 936 | 0 |
Smaug Slerp 30B V0.1 | 0.2 | 32K / 60.4 GB | 299 | 0 |
Llama33b 16K | 0.1 | 16K / 65.2 GB | 8 | 1 |
Yayi2 30B Llama | 0.2 | 4K / 121.2 GB | 956 | 22 |
... Tokens By Perplexity Bottom K | 0.2 | 4K / 5.4 GB | 17 | 0 |
...lue Sample With Temperature2.0 | 0.2 | 4K / 5.4 GB | 13 | 0 |
... Tokens By Writing Style Top K | 0.2 | 4K / 5.4 GB | 9 | 0 |
...via Sample With Temperature2.0 | 0.2 | 4K / 5.4 GB | 8 | 0 |
Yayi2 30B Guanaco | 0.2 | 4K / 60.6 GB | 10 | 2 |
Llama 30B Instruct 2048 | 0.2 | 2K / 65.2 GB | 2601 | 103 |
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