olmo7-think-sft-hyp / README.md
zimplex's picture
Add model card
07590b3 verified
|
Raw
History Blame Contribute Delete
1.23 kB
metadata
license: apache-2.0
base_model: allenai/Olmo-3-1025-7B
pipeline_tag: text-generation
tags:
  - olmo
  - reasoning
  - sft
  - hyperbolic
  - think

zimplex/olmo7-think-sft-hyp

Thinking-SFT of allenai/Olmo-3-1025-7B on allenai/Dolci-Think-SFT-7B with a hyperbolic (Lorentzian) output head (output-only, curvature c = 0.05), trained with the <think> ChatML template.

IMPORTANT — the hyperbolic head is not the standard lm_head

A plain AutoModelForCausalLM.from_pretrained(...) loads the euclidean head and gives the WRONG model. To use the hyperbolic head you must load hyp_head_state.pt and swap the output head using the training repo's code (scripts/eval_think.pyload_hyp_head / HyperbolicLMHead; the vLLM path mirrors it). hyp_head_state.pt is authoritative for curvature / scale / projection / adapter.

Prompting & grading

Use the repo's <think> template (openrlhf/utils/think_chat.py); greedy decoding. Take the answer after </think> (last \boxed{} / #### / number) and grade math with math_verify.

Files

Standard HF Olmo3 weights + tokenizer + chat_template.jinja, plus hyp_head_state.pt (vocab_emb, down_proj, log_input_scale, log_temp, curvature).