Instructions to use dongbobo/adapter-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dongbobo/adapter-checkpoint with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "dongbobo/adapter-checkpoint") - Notebooks
- Google Colab
- Kaggle
Download examples/chat/zero_shot/prompt.json from dongbobo/adapter-checkpoint: direct link, hf CLI and curl.
- Browser
- Download file 660 Bytes
-
https://huggingface.co/dongbobo/adapter-checkpoint/resolve/main/examples/chat/zero_shot/prompt.json
- Command line
-
hf download hf://dongbobo/adapter-checkpoint/examples/chat/zero_shot/prompt.json
-
curl -L -o prompt.json https://huggingface.co/dongbobo/adapter-checkpoint/resolve/main/examples/chat/zero_shot/prompt.json
660 Bytes
| { | |
| "type": "zero_shot", | |
| "description": "Zero-shot chat prompt template — no examples provided; the model relies entirely on its instruction-following capability.", | |
| "template": { | |
| "system": "You are a helpful, respectful, and honest assistant. Answer the user's question as clearly and concisely as possible.", | |
| "user": "{{user_message}}", | |
| "assistant": "" | |
| }, | |
| "variables": [ | |
| { | |
| "name": "user_message", | |
| "description": "The user's input message or question.", | |
| "required": true | |
| } | |
| ], | |
| "example": { | |
| "user_message": "What is the capital of France?", | |
| "expected_response": "The capital of France is Paris." | |
| } | |
| } | |