# PhysisML in ollama.
#
#   python3 scripts/export_gguf.py \
#       --checkpoint models/checkpoints/it/level_12/final_dreamed.pt \
#       --tokenizer  models/checkpoints/it/level_12/tokenizer.json \
#       --output     models/physisml.gguf
#   ollama create physisml -f Modelfile && ollama run physisml
#
# TEMPLATE is the bare prompt: the model was taught single-turn question/answer
# lines, so any chat wrapper is out of distribution. Greedy because the margin
# is thin and the published scores are measured that way.
#
# No stop strings: the model emits <|EOS|> on its own since the corpus started
# carrying it (P(EOS) after a finished answer went from 0.00004 to 0.85-1.00).
# It used to need `PARAMETER stop . ! ?` , which also ate the final punctuation.
#
# `ollama run` INTERACTIVELY sends the accumulated conversation back as context.
# With a 128-token window and no multi-turn training, three exchanges are enough
# to crowd out the question: 'cosa fa la mamma?' answers 'la mamma mangia' alone
# and 'il cane' with the previous turns prepended. Use /clear, one-shot
# `ollama run physisml "..."`, or the API — all three are stateless.
FROM ./physisml.gguf
TEMPLATE {{ .Prompt }}
PARAMETER temperature 0
PARAMETER top_k 1
PARAMETER num_predict 48
PARAMETER num_ctx 128
PARAMETER repeat_penalty 1