LLM Name | WizardLM Uncensored SuperCOT StoryTelling 30B SuperHOT 8K 4bit 32g |
Repository ๐ค | https://huggingface.co/Panchovix/WizardLM-Uncensored-SuperCOT-StoryTelling-30b-SuperHOT-8k-4bit-32g |
Base Model(s) | |
Model Size | 30b |
Required VRAM | 19.4 GB |
Updated | 2024-09-19 |
Maintainer | Panchovix |
Model Type | llama |
Model Files | |
Context Length | 8k |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | other |
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 | 32001 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...rd Vicuna 30B Superhot 8K Fp16 | 8K / 65.2 GB | 732 | 7 |
...ryTelling 30B SuperHOT 8K Fp16 | 8K / 65.2 GB | 12 | 8 |
...ard Vicuna 30B Uncensored Fp16 | 2K / 65.2 GB | 723 | 17 |
...d Lxctx PI 16384 LoRA 4bit 32g | 2K / 19.4 GB | 9 | 4 |
...nAssistant 30B Uncensored 4bit | 2K / 18.1 GB | 6 | 7 |
Tenebra 30B Alpha01 FP16 | 16K / 65 GB | 701 | 4 |
Tenebra 30B Alpha01 4BIT | 16K / 19.4 GB | 727 | 1 |
...nebra 30B Alpha01 EXL2 2 80bpw | 16K / 11.9 GB | 7 | 1 |
Tenebra 30B Alpha01 EXL2 3bpw | 16K / 12.7 GB | 10 | 0 |
Tenebra 30B Alpha01 3BIT | 16K / 12.9 GB | 15 | 0 |
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