This model was trained using Unsloth's continuous pretraining with the ChatML format with 24k context.
This model was used to create
TheTsar1209/qwen-carpmuscle-r-v0.3 except instead of changing the base to
Qwen/Qwen2.5-14B-Instruct the base was kept to
Qwen/Qwen2.5-14B.
This qwen2 model was trained 2x faster with
Unsloth and Huggingface's TRL library.
