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 13B Uncensored GPTQ Benchmarks
ARC: 29.61 vs 96.7 (so35)-69.4%
HellaSwag: 25.47 vs 95.3 (gpt4)-73.3%
MMLU: 25.34 vs 88.3 (so35)-71.3%
TruthfulQA: 50.25 vs 59 (gpt4)-14.8%
WinoGrande: 75.77 vs 87.5 (gpt4)-13.4%
GSM8K: 9.93 vs 96.4 (so35)-89.7%
LLME Score: 0.22434
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 13B Uncensored GPTQ Parameters and Internals
| LLM Name | Wizard Vicuna 13B Uncensored GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ |
| Model Name | Wizard Vicuna 13B Uncensored |
| Model Creator | Eric Hartford |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 8.1 GB |
| Updated | 2024-09-16 |
| 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 | 4.28.1 |
| 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 13B Uncensored GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...3B Uncensored SuperHOT 8K GPTQ | 8K / 7.5 GB | 572 | 135 |
| ....0 Uncensored SuperHOT 8K GPTQ | 8K / 7.5 GB | 36 | 47 |
| ...3B Uncensored SuperHOT 8K GPTQ | 8K / 7.5 GB | 5 | 3 |
| Uncensored Jordan 13B GPTQ | 4K / 7.3 GB | 12 | 8 |
| Uncensored Frank 13B GPTQ | 4K / 7.3 GB | 23 | 3 |
| Guanaco 13B Uncensored GPTQ | 4K / 7.3 GB | 11 | 5 |
| ...1.0 Uncensored Llama2 13B GPTQ | 4K / 7.3 GB | 78 | 52 |
| ...Vicuna 13B Uncensored AutoGPTQ | 2K / 8.1 GB | 6 | 1 |
| ...lama2 13b Chat Uncensored GPTQ | 2K / 7.3 GB | 18 | 3 |
| ...MegaCoder Llama2 13B Mini GPTQ | 2K / 7.3 GB | 14 | 4 |
Rank the Wizard Vicuna 13B 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803