The largest version of the chan shitpost 2.5 llmama family. It includes the tokens "<|begin_of_text|>" and "<|end_of_text|>" Trained on the same data but with added special tokens. Old version (Simular, but smaller and no special tokens): https://huggingface.co/simonko912/chan-shitpost-2.5-llama-large Example:

<|begin_of_text|>What about you?<|end_of_text|>
Anonymous: <|begin_of_text|>Bored<|end_of_text|>
Ley: <|begin_of_text|>Kik CDY<|end_of_text|>
Anonymous: <|begin_...
Downloads last month
-
Safetensors
Model size
0.4B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train simonko912/chan-shitpost-2.5-llama-largest