Didn't really have any cool README ideas for this so we're just going with just whatever song i'm listening to rn and it happened to be Baby i'm bleeding
Nevertheless, This is a finetune from the 32K context extended (or fixed?) Arcee GLM4 base - Trained shrimply with just the Tulu-SFT-Mixture but I removed Safety alignment examples. Came out pretty well, It uses chatML due to the GLM4 Format giving me a headache. It's a decently competant assistant although I haven't done any testing on how well the model performs at longer-contexts, nor have i done any RL afterwards to fix up it's edges.
Think it should be a decent base for any future finetunes, I felt that GLM4 really wasn't given the proper time of day and it's a way better base then any Qwen3 model.
"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
