Instructions to use Shrishml/dolly_lora3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Shrishml/dolly_lora3b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-3b") model = PeftModel.from_pretrained(base_model, "Shrishml/dolly_lora3b") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from Shrishml/dolly_lora3b: direct link, hf CLI and curl.
- Browser
- Download file 471 Bytes
-
https://huggingface.co/Shrishml/dolly_lora3b/resolve/main/adapter_config.json
- Command line
-
hf download hf://Shrishml/dolly_lora3b/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/Shrishml/dolly_lora3b/resolve/main/adapter_config.json
471 Bytes
| { | |
| "base_model_name_or_path": "databricks/dolly-v2-3b", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 16, | |
| "revision": null, | |
| "target_modules": [ | |
| "query_key_value", | |
| "dense", | |
| "dense_h_to_4h", | |
| "dense_4h_to_h" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |