Instructions to use bigcode/astraios-3b-ptuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bigcode/astraios-3b-ptuning with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase-3b") model = PeftModel.from_pretrained(base_model, "bigcode/astraios-3b-ptuning") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "bigcode/starcoderbase-3b", | |
| "encoder_dropout": 0.0, | |
| "encoder_hidden_size": 2816, | |
| "encoder_num_layers": 2, | |
| "encoder_reparameterization_type": "MLP", | |
| "inference_mode": true, | |
| "num_attention_heads": 22, | |
| "num_layers": 36, | |
| "num_transformer_submodules": 1, | |
| "num_virtual_tokens": 30, | |
| "peft_type": "P_TUNING", | |
| "revision": null, | |
| "task_type": "CAUSAL_LM", | |
| "token_dim": 2816 | |
| } |