Today
-
Model card: comparison with recent small base models by kind of text
-
Model card: comparison with Pythia-160M and SmolLM2-135M by parameters and training tokens
-
Model card: link PhiloText, CPU speed, intended uses, Python loading, corrected context length
-
PhiloLM: the model card under its name
-
Model card: highlights and model overview, parameters counted as for n-gram models
-
Model card: non-embedding and total parameter counts
-
philosophy-lm: float32 weights
-
philosophy-lm: model card, code, tokenizer and browser files
-
initial commit