RGB / report.txt
SelvaKrish's picture
Upload 9 files
84bf79a verified
raw
history blame contribute delete
785 Bytes
Noise Level 0.3 (en Dataset)
"llama-3.1-8b-instant" -> Done
"llama-3.3-70b-versatile", -> Done # Remove
"gemma2-9b-it" -> Done
"deepseek-r1-distill-llama-70b" -> Done
"qwen/qwen3-32b" -> Done
Noise Level 0.0
Noise Level 0.2
Noise Level 0.4
Noise Level 0.6
Noise Level 0.8
Noise Level 1.0
==========================
Information Integration (4 Models) => @Krishna [en_int] Dataset
Noise Level 0.0
Noise Level 0.2
Noise Level 0.4
Noise Level 0.6
Noise Level 0.8
Metric Negative Rejection
python reject_evalue.py \
--dataset en \
--modelname chatglm2-6b \
--api_key YourAPIKEY
Run on 4 Models
python reject_evalue.py \
--dataset en \
--modelname chatglm2-6b \
--api_key YourAPIKEY