Instructions to use HexawareTech/chat-faq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HexawareTech/chat-faq with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HexawareTech/chat-faq", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "HexawareTech/phi2-base-model", | |
| "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": 64, | |
| "revision": null, | |
| "target_modules": [ | |
| "Wqkv", | |
| "out_proj", | |
| "fc1", | |
| "fc2" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |