LFM2.5 8B A1B Hermes Agentic Coder Abliterated V3 LoRA is an open-source language model by DuoNeural. Features: 8b LLM, VRAM: 0.1GB, License: other, Code Generating, LLM Explorer Score: 0.27.
| LLM Name | LFM2.5 8B A1B Hermes Agentic Coder Abliterated V3 LoRA |
| Repository 🤗 | https://huggingface.co/DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-LoRA |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.1 GB |
| Updated | 2026-09-22 |
| Maintainer | DuoNeural |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | Adapter |
| License | other |
| Is Biased | none |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | out_proj|v_proj|q_proj|classifier|in_proj|w1|w3|k_proj|w2 |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.05 |
| R Param | 64 |