8-bit Adapter Base model:adapter:nousresearc... Base model:nousresearch/llama-... Bitsandbytes Finetuned Generated from trainer Llama Lora Peft Region:us Safetensors
Toxicqa Llama2 13B Lora Benchmarks
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)
Toxicqa Llama2 13B Lora Parameters and Internals
| LLM Name | Toxicqa Llama2 13B Lora |
| Repository 🤗 | https://huggingface.co/Undi95/toxicqa-Llama2-13B-lora |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 2 GB |
| Updated | 2024-09-07 |
| Maintainer | Undi95 |
| Model Files | |
| Model Architecture | Adapter |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|gate_proj|up_proj|v_proj|o_proj|q_proj|down_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 128 |
Best Alternatives to Toxicqa Llama2 13B Lora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...10 2024 06 23 06 24 24 3558635 | 0K / 0.8 GB | 6 | 0 |
| ...10 2024 06 22 21 11 23 3558624 | 0K / 0.8 GB | 6 | 0 |
| LLaMA2 13B Stop Hate | 0K / 0.5 GB | 3 | 1 |
| Llama 2 13b Vacancies Lora | 0K / 0.1 GB | 0 | 1 |
| Llama2 13B Qlora Openassistant | 0K / 0.3 GB | 6 | 1 |
| ...ation Llama2 13b Climate Fever | 0K / 26 GB | 2 | 1 |
| Typescript Instruct 20K V4 | 0K / 26 GB | 2 | 1 |
| Llama 2 13B Chat Es | 0K / 0.2 GB | 80 | 1 |
| Llama 2 13B Chat Fr | 0K / 0.2 GB | 70 | 0 |
| Typescript Instruct 20K V2 | 0K / 26 GB | 23 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than Undi95/toxicqa-Llama2-13B-lora .
Rank the Toxicqa Llama2 13B Lora 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803