AIRLab-POLIMI/codellama-7b-instruct-hf-btgenbot-adapter

LoRA adapter release for the paper BTGenBot: Behavior Tree Generation for Robotic Tasks with Lightweight LLMs, currently in submission at IEEE/RSJ International Conference on Intelligent Robots and Systems. `GitHub Repository` `Paper `

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• —Developed by: Riccardo Andrea Izzo
• —Model type: Transformer-based language model
• —Language(s) (NLP): English
• —Finetuned from model [optional]: CodeLlama-7b-Instruct-hf

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• —Repository: codellama/CodeLlama-7b-Instruct-hf

Uses

Behavior trees generation for robotic tasks

Hardware infrastructure

• —Hardware Type: 2x NVIDIA Quadro RTX 6000
• —Hours used: 36h

Training procedure

The following bitsandbytes quantization config was used during training:

• —quant_method: bitsandbytes
• —loadin8bit: True
• —loadin4bit: False
• —llmint8threshold: 6.0
• —llmint8skip_modules: None
• —llmint8enablefp32cpu_offload: False
• —llmint8hasfp16weight: False
• —bnb4bitquant_type: fp4
• —bnb4bitusedoublequant: False
• —bnb4bitcompute_dtype: float32

Framework versions

• —PEFT 0.6.0