Instructions to use Gustrd/mpt-7b-lora-cabra3-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Gustrd/mpt-7b-lora-cabra3-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("HachiML/mpt-7b-instruct-for-peft") model = PeftModel.from_pretrained(base_model, "Gustrd/mpt-7b-lora-cabra3-adapter") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from Gustrd/mpt-7b-lora-cabra3-adapter: direct link, hf CLI and curl.
- Browser
- Download file 488 Bytes
-
https://huggingface.co/Gustrd/mpt-7b-lora-cabra3-adapter/resolve/8ac1db557560c574286c3ac581163effc3e8f1fb/adapter_config.json
- Command line
-
hf download hf://Gustrd/mpt-7b-lora-cabra3-adapter@8ac1db557560c574286c3ac581163effc3e8f1fb/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/Gustrd/mpt-7b-lora-cabra3-adapter/resolve/8ac1db557560c574286c3ac581163effc3e8f1fb/adapter_config.json
488 Bytes
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "HachiML/mpt-7b-instruct-for-peft", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 64, | |
| "revision": null, | |
| "target_modules": [ | |
| "Wqkv", | |
| "out_proj", | |
| "up_proj", | |
| "down_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |