SmolVLM Instruct DPO is an open-source language model by HuggingFaceTB. Features: 1.7b LLM, VRAM: 0.1GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.16.
| LLM Name | SmolVLM Instruct DPO |
| Repository 🤗 | https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 0.1 GB |
| Updated | 2026-08-11 |
| Maintainer | HuggingFaceTB |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Model Max Length | 16384 |
| Is Biased | none |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49152 |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | fc2|up_proj|down_proj|fc1|out_proj|gate_proj|proj|q_proj|k_proj|o_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |