Instructions to use DevQuasar/analytical_reasoning_Llama-3.2-1B_adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use DevQuasar/analytical_reasoning_Llama-3.2-1B_adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-1B-bnb-4bit") model = PeftModel.from_pretrained(base_model, "DevQuasar/analytical_reasoning_Llama-3.2-1B_adapter") - Notebooks
- Google Colab
- Kaggle
metadata
license: llama3.2
base_model: unsloth/Llama-3.2-1B-bnb-4bit
library_name: peft
datasets:
- microsoft/orca-agentinstruct-1M-v1
pipeline_tag: text-generation
'Make knowledge free for everyone'
Prompt format:
"input_prefix": "### Instruction:\\n",
"input_suffix": "\\n### Response:\\n",
"antiprompt": [
"### Instruction:"
],
