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

Detailed results can be found here

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
Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for joehuangx/spatial-vicuna-7b-v1.5-LoRA

Adapter
(27)
this model

Spaces using joehuangx/spatial-vicuna-7b-v1.5-LoRA 21