4-bit Autotrain compatible Base model:cognitivecomputatio... Base model:quantized:cognitive... Dataset:ehartford/wizardlm alp... Gptq Instruct Llama Quantized Region:us Safetensors Uncensored
WizardLM 30B Uncensored GPTQ Benchmarks
ARC: 29.44 vs 96.7 (so35)-69.6%
HellaSwag: 26.47 vs 95.3 (gpt4)-72.2%
MMLU: 24.35 vs 88.3 (so35)-72.4%
TruthfulQA: 49.15 vs 59 (gpt4)-16.7%
WinoGrande: 73.16 vs 87.5 (gpt4)-16.4%
GSM8K: 21.08 vs 96.4 (so35)-78.1%
LLME Score: 0.17269
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)
WizardLM 30B Uncensored GPTQ Parameters and Internals
| LLM Name | WizardLM 30B Uncensored GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/WizardLM-30B-Uncensored-GPTQ |
| Model Name | Wizardlm 30B Uncensored |
| Model Creator | Eric Hartford |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 16.9 GB |
| Updated | 2024-09-18 |
| Maintainer | TheBloke |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| 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 | 32001 |
| Torch Data Type | float16 |
Best Alternatives to WizardLM 30B Uncensored GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...e Llama 30B Instruct 2048 GPTQ | 2K / 16.9 GB | 16 | 23 |
| H2ogpt Oasst1 512 30B GPTQ | 2K / 16.9 GB | 9 | 5 |
| ...nsored Instruct PL Lora Unload | 2K / 65.2 GB | 686 | 0 |
| WizardLM 30B Uncensored AWQ | 2K / 17.6 GB | 20 | 4 |
| WizardLM 30B Uncensored | 2K / 65.2 GB | 734 | 138 |
| ...ncensored Guanaco SuperCOT 30B | 2K / 65.2 GB | 696 | 24 |
| Llama 30B Instruct 2048 | 2K / 65.2 GB | 4300 | 103 |
| ...ct 2048 Open Platypus 100steps | 2K / 65.2 GB | 708 | 0 |
| ...azarus Instruct PL Lora Unload | 2K / 65.2 GB | 695 | 0 |
| ...B 2048 Instruct PL Lora Unload | 2K / 65.2 GB | 708 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/WizardLM-30B-Uncensored-GPTQ .
Rank the WizardLM 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803