metadata
library_name: peft
Training procedure
The following bitsandbytes
quantization config was used during training:
- 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 0.4.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 45.53 |
ARC (25-shot) | 55.72 |
HellaSwag (10-shot) | 78.75 |
MMLU (5-shot) | 47.99 |
TruthfulQA (0-shot) | 43.11 |
Winogrande (5-shot) | 75.85 |
GSM8K (5-shot) | 10.77 |
DROP (3-shot) | 6.53 |