4-bit Autotrain compatible Base model:cognitivecomputatio... Base model:quantized:cognitive... Dataset:ehartford/wizard vicun... En Gptq Llama Quantized Region:us Safetensors Uncensored
Wizard Vicuna 30B Uncensored GPTQ Benchmarks
ARC: 61.09 vs 96.7 (so35)-36.8%
HellaSwag: 82.4 vs 95.3 (gpt4)-13.5%
MMLU: 56.46 vs 88.3 (so35)-36.1%
TruthfulQA: 49.9 vs 59 (gpt4)-15.4%
WinoGrande: 77.66 vs 87.5 (gpt4)-11.2%
GSM8K: 23.28 vs 96.4 (so35)-75.9%
LLME Score: 0.19345
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Wizard Vicuna 30B Uncensored GPTQ Parameters and Internals
| LLM Name | Wizard Vicuna 30B Uncensored GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ |
| Model Name | Wizard Vicuna 30B Uncensored |
| Model Creator | Eric Hartford |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 16.9 GB |
| Updated | 2024-09-19 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.30.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Wizard Vicuna 30B Uncensored GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ryTelling 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 26 | 47 |
| ...rd Vicuna 30B Superhot 8K GPTQ | 8K / 16.9 GB | 29 | 20 |
| ...SuperCOT StoryTelling 30B GPTQ | 2K / 16.9 GB | 86 | 84 |
| WizardLM 30B Uncensored GPTQ | 2K / 16.9 GB | 38 | 117 |
| ...30B Guanaco SuperCOT GPTQ 4bit | 2K / 16.9 GB | 7 | 9 |
| ...rd Vicuna 30B Superhot 8K Fp16 | 8K / 65.2 GB | 732 | 7 |
| GPlatty 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 9 | 7 |
| ...ryTelling 30B SuperHOT 8K Fp16 | 8K / 65.2 GB | 12 | 8 |
| Platypus 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 15 | 4 |
| ... 30B Supercot SuperHOT 8K GPTQ | 8K / 16.9 GB | 10 | 5 |
Rank the Wizard Vicuna 30B Uncensored GPTQ Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 36030 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803