Instructions to use bigcode/astraios-parallel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bigcode/astraios-parallel with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase") model = PeftModel.from_pretrained(base_model, "bigcode/astraios-parallel") - Notebooks
- Google Colab
- Kaggle
| { | |
| "adapter_dropout": 0.0, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "bigcode/starcoderbase", | |
| "bias": "none", | |
| "bottleneck_size": 256, | |
| "inference_mode": true, | |
| "init_weights": "bert", | |
| "modules_to_save": null, | |
| "non_linearity": "tanh", | |
| "peft_type": "BOTTLENECK", | |
| "revision": null, | |
| "scaling": 1.0, | |
| "target_modules": [ | |
| "c_attn", | |
| "q_attn" | |
| ], | |
| "task_type": "CAUSAL_LM", | |
| "use_adapterp": false, | |
| "use_parallel_adapter": true | |
| } |