Model Card on HF 🤗: https://huggingface.co/dickdiss/llama3_qlora
Llama3 Qlora 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)
Llama3 Qlora Parameters and Internals
| LLM Name | Llama3 Qlora |
| Repository 🤗 | https://huggingface.co/dickdiss/llama3_qlora |
| Required VRAM | 0.1 GB |
| Updated | 2025-02-22 |
| Maintainer | dickdiss |
| Model Files | |
| Model Architecture | AutoModel |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|down_proj|o_proj|q_proj|up_proj|k_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Llama3 Qlora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Distil Longformer Base 4096 | 4K / 0.4 GB | 126 | 0 |
| Daedalus 1 | 1K / GB | 17 | 1 |
| Opengpt2 Pytorch Backward | 1K / 6 GB | 165 | 1 |
| Tiny Random Detr | 1K / 0.2 GB | 162 | 0 |
| Opengpt2 Pytorch Forward | 1K / 6 GB | 118 | 1 |
| Finsent Transformer | 0.5K / 0.4 GB | 6 | 1 |
| Bert Chinese L 12 H 768 A 12 | 0.5K / 0.4 GB | 150 | 1 |
| Simbert Chinese Base | 0.5K / 0.4 GB | 149 | 0 |
| Simbert Chinese Tiny | 0.5K / 0 GB | 59 | 0 |
| All MiniLM L12 V2 | 0.5K / GB | 2095 | 3 |
Rank the Llama3 Qlora 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227