Hugging Face's logo

zjotero
/
Qwen2.5-1.5B-think-spkd

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
sft
trl
conversational
text-generation-inference
Model card Files
xet
Community
Qwen2.5-1.5B-think-spkd
File size: 182 Bytes 
b4a6e80
 
1
2
 
[2025-11-30 01:59:24,307][accelerate.accelerator][WARNING] - Gradient accumulation steps mismatch: GradientAccumulationPlugin has 1, DeepSpeed config has 2. Using DeepSpeed's value.