Text Generation
PEFT
Safetensors
smollm3
lora
context-compression
agent-memory
membrane
conversational
Instructions to use homerquan/mn-context-engine-lora-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use homerquan/mn-context-engine-lora-v2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM3-3B") model = PeftModel.from_pretrained(base_model, "homerquan/mn-context-engine-lora-v2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "backend": "tokenizers", | |
| "bos_token": null, | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|im_end|>", | |
| "fast": false, | |
| "is_local": false, | |
| "local_files_only": false, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 131072, | |
| "pad_token": "<|im_end|>", | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |