chloeli
/

qwen-2.5-0.5B-instruct-sft-lora-countdown-deepseek-correct-seq8k-1k

Text Generation

Generated from Trainer

alignment-handbook

text-generation-inference

Model card Files Files and versions Community

qwen-2.5-0.5B-instruct-sft-lora-countdown-deepseek-correct-seq8k-1k

Commit History

Improve language tag

884cdee
verified

lbourdois commited on 12 days ago

End of training

d5f268e
verified

chloeli commited on Apr 4

Model save

3407f61
verified

chloeli commited on Apr 4

Training in progress, step 125

f299eb5
verified

chloeli commited on Apr 4

Training in progress, step 100

fab51b6
verified

chloeli commited on Apr 4

initial commit

fb20555
verified

chloeli commited on Apr 4