Instructions to use luna-code/codegen-350M-mono-evo-prefix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use luna-code/codegen-350M-mono-evo-prefix with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-350M-mono") model = PeftModel.from_pretrained(base_model, "luna-code/codegen-350M-mono-evo-prefix") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "Salesforce/codegen-350M-mono", | |
| "encoder_hidden_size": 1024, | |
| "inference_mode": true, | |
| "num_attention_heads": 16, | |
| "num_layers": 20, | |
| "num_transformer_submodules": 1, | |
| "num_virtual_tokens": 5, | |
| "peft_type": "PREFIX_TUNING", | |
| "prefix_projection": false, | |
| "revision": null, | |
| "task_type": "CAUSAL_LM", | |
| "token_dim": 1024 | |
| } |