4bit Autotrain compatible Dataset:lajonbot/alpaca-dolly-... Endpoints compatible Facebook Gptq Instruct Llama Llama2 Lora Meta Pl Pytorch Quantized Region:us Uncensored
WizardVicuna Uncensored 3B Instruct PL Lora GPTQ Benchmarks
ARC: 41.98 vs 96.7 (so35)-56.6%
HellaSwag: 66.82 vs 95.3 (gpt4)-29.9%
MMLU: 25.69 vs 88.3 (so35)-70.9%
TruthfulQA: 39.67 vs 59 (gpt4)-32.8%
WinoGrande: 64.88 vs 87.5 (gpt4)-25.9%
GSM8K: 0.68 vs 96.4 (so35)-99.3%
LLME Score: 0.17498
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)
WizardVicuna Uncensored 3B Instruct PL Lora GPTQ Parameters and Internals
| LLM Name | WizardVicuna Uncensored 3B Instruct PL Lora GPTQ |
| Repository 🤗 | https://huggingface.co/Aspik101/WizardVicuna-Uncensored-3B-instruct-PL-lora_GPTQ |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 2.1 GB |
| Updated | 2024-10-08 |
| Maintainer | Aspik101 |
| Model Type | llama-2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | pl |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.32.0.dev0 |
| Vocabulary Size | 32000 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to WizardVicuna Uncensored 3B Instruct PL Lora GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Evil Alpaca 3B L3.2 | 128K / 6.5 GB | 29 | 0 |
| ...B GPTQ 4bit GPTQ Code Instruct | 2K / 2 GB | 15 | 0 |
| ...zard Evol Instuct V2 196K GPTQ | 2K / 2.1 GB | 4 | 2 |
| ...ama 3.2 3B Instruct Uncensored | 128K / 7.2 GB | 12152 | 41 |
| Llama 3.2 3B Instruct Bnb 4bit | 128K / 2.2 GB | 142578 | 11 |
| Llama 3.2 3B Instruct 4bit | 128K / 1.8 GB | 5698 | 7 |
| ...ma 3.2 3B Instruct Abliterated | 128K / 7.2 GB | 800 | 12 |
| Reasoning Llama 3B V0.1 | 128K / 6.5 GB | 85 | 4 |
| ...nstruct Medical Conversational | 128K / 6.5 GB | 264 | 3 |
| ...olio Query Llama 3.2 3B V3 Cot | 128K / 6.5 GB | 169 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Aspik101/WizardVicuna-Uncensored-3B-instruct-PL-lora_GPTQ .
Rank the WizardVicuna Uncensored 3B Instruct PL Lora 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? 36894 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803