| library_name: peft | |
| base_model: lmsys/vicuna-7b-v1.5 | |
| ## Training procedure | |
| The following `bitsandbytes` quantization config was used during training: | |
| - quant_method: bitsandbytes | |
| - load_in_8bit: False | |
| - load_in_4bit: True | |
| - 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: nf4 | |
| - bnb_4bit_use_double_quant: True | |
| - bnb_4bit_compute_dtype: bfloat16 | |
| ### Framework versions | |
| - PEFT 0.6.0.dev0 | |
| # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | |
| Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_joehuangx__spatial-vicuna-7b-v1.5-LoRA) | |
| | Metric | Value | | |
| |-----------------------|---------------------------| | |
| | Avg. | 44.55 | | |
| | ARC (25-shot) | 50.77 | | |
| | HellaSwag (10-shot) | 74.63 | | |
| | MMLU (5-shot) | 48.13 | | |
| | TruthfulQA (0-shot) | 49.36 | | |
| | Winogrande (5-shot) | 72.38 | | |
| | GSM8K (5-shot) | 6.9 | | |
| | DROP (3-shot) | 9.72 | | |