Text Generation
PEFT
Safetensors
English
lora
llama-3.1
api-generation
function-calling
structured-output
fine-tuned
conversational
Instructions to use kineticdrive/llama-structured-api-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use kineticdrive/llama-structured-api-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.1-8b-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "kineticdrive/llama-structured-api-adapter") - Notebooks
- Google Colab
- Kaggle
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT)
02e3cea verified - Xet hash:
- c4530699d0209a307783c8d39f35cd73dc23b5429abaaa6604036ce2b1b2ebf2
- Size of remote file:
- 17.2 MB
- SHA256:
- 9c85066e7642934ed09b44155e6566b0b5dab2637fb9433439ba5c9c7f8b50d3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.