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

Model Details

Model Description

• 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]

• 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
• load_in_8bit: True
• load_in_4bit: False
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: fp4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float32

Framework versions

• PEFT 0.6.0