Structuraai Aya Expanse 8B Finetuned Extractor is an open-source language model by rakesh-bishnoi29. Features: 8b LLM, VRAM: 0.2GB, License: cc-by-nc-4.0, Fine-Tuned, LLM Explorer Score: 0.31.
| LLM Name | Structuraai Aya Expanse 8B Finetuned Extractor |
| Repository 🤗 | https://huggingface.co/rakesh-bishnoi29/structuraai-aya-expanse-8b-finetuned-extractor |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.2 GB |
| Updated | 2026-11-13 |
| Maintainer | rakesh-bishnoi29 |
| Model Files | |
| Model Architecture | Adapter |
| License | cc-by-nc-4.0 |
| Is Biased | none |
| Tokenizer Class | CohereTokenizer |
| Padding Token | <PAD> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | o_proj|v_proj|q_proj|gate_proj|down_proj|up_proj|k_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 10 | 0 |
| HybridAgent 8B Agentic | 0K / 0.1 GB | 1555 | 12 |
| Qwen3 8B Tawny Owl 128 Neurons | 0K / 0.2 GB | 259 | 4 |
| K Oss 8 Mini Instruct Beta | 0K / 0.2 GB | 50 | 1 |
| Torchlight Qwen3 8B Lora | 0K / 0.2 GB | 23 | 1 |
| ...Max H3 Prompt Rewriter LoRA 8B | 0K / 2.8 GB | 137 | 26 |
| Triage Qwen3 8B Public V5 | 0K / 0.2 GB | 15 | 1 |
| ...te 4.2 8B Msvc2008 Decomp Lora | 0K / 0.8 GB | 15 | 1 |
| Llama3 8B Persian Lora | 0K / 0.2 GB | 22 | 1 |
| Velora V1 | 0K / 0 GB | 26 | 1 |