Model Card on HF 🤗: https://huggingface.co/Neko-Institute-of-Science/guanaco-unchained-33b-qlora
Guanaco Unchained 33B 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)
Guanaco Unchained 33B Qlora Parameters and Internals
| Model Type |
| |||||||||
| Additional Notes |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | Guanaco Unchained 33B Qlora |
| Repository 🤗 | https://huggingface.co/Neko-Institute-of-Science/guanaco-unchained-33b-qlora |
| Model Size | 33b |
| Required VRAM | 1 GB |
| Updated | 2025-09-14 |
| Maintainer | Neko-Institute-of-Science |
| Model Files | |
| Model Architecture | Adapter |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|o_proj|up_proj|gate_proj|q_proj|v_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 64 |
Best Alternatives to Guanaco Unchained 33B Qlora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MentaLLaMA 33B Lora | 0K / 0.1 GB | 0 | 5 |
| Airoboros 33B 2.1 Peft | 0K / 1 GB | 0 | 1 |
| Chinese Alpaca Pro Lora 33B | 0K / 2.3 GB | 0 | 7 |
| Chinese Alpaca Plus Lora 33B | 0K / 2.3 GB | 0 | 2 |
| Sorceroboros 33B S2a4 Qlora | 0K / 1.9 GB | 1 | 1 |
| Llama 33B Lxctx PI 16384 LoRA | 0K / 1 GB | 0 | 2 |
| ...Gpt4 1.4.1 Lxctx PI 16384 LoRA | 0K / 1 GB | 0 | 1 |
| Enterredaas 33B QLoRA | 0K / 1 GB | 0 | 4 |
| ... 33B Gpt4 1.4.1 NTK 16384 LoRA | 0K / 1 GB | 0 | 2 |
| Chinese Alpaca Lora 33B | 0K / 2.9 GB | 0 | 10 |
Note: green Score (e.g. "73.2") means that the model is better than Neko-Institute-of-Science/guanaco-unchained-33b-qlora .
Rank the Guanaco Unchained 33B 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? 51368 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124