4-bit Adapter Base model:adapter:athirdpath/... Base model:athirdpath/epsilon-... Bitsandbytes Finetuned Generated from trainer Lora Mistral Peft Region:us
Model Card on HF 🤗: https://huggingface.co/athirdpath/Zeta-17b_LORA
Zeta 17b 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)
Zeta 17B LORA Parameters and Internals
| LLM Name | Zeta 17b LORA |
| Repository 🤗 | https://huggingface.co/athirdpath/Zeta-17b_LORA |
| Base Model(s) | |
| Model Size | 17b |
| Required VRAM | 0.8 GB |
| Updated | 2025-09-12 |
| Maintainer | athirdpath |
| Model Files | |
| Model Architecture | Adapter |
| License | cc-by-nc-4.0 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|k_proj|gate_proj|q_proj|v_proj|up_proj|o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.06 |
| R Param | 32 |
Rank the Zeta 17B 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124