babyconceptLM-English-matched

English matched BabyConceptLM

This repository contains the frozen English BabyConceptLM checkpoint used as the concept-side reference in the paper's matched-control comparison with zondaxyz/babyconceptLM-TA1-token-only-en.

This is the archived e3_583_eng100m_full_dwa_A_stable experiment, not the distinct public-final BabyLM submission in zondaxyz/babyconceptLM-583-en.

Identity

• Architecture profile: 5 token-encoder / 8 concept-backbone / 3 readout layers
• Parameters: 194,574,142
• Original experiment identifier: e3_583_eng100m_full_dwa_A_stable
• pytorch_model.bin SHA-256: 55ba4c4cb71dfa102ce283ee67f8ab5d9cd6abb7eeb5e038a38266dff6836ba8
• Training seed: 42
• Frozen training steps: 97,750

The repository includes the tokenizer, configuration, model weights, and custom Transformers-compatible loading code. The optimizer/training state is intentionally omitted because it is not required for inference or frozen evaluation. Machine-specific absolute paths from the original training summary are also omitted; a portable recipe summary is provided in matched_provenance.json.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "zondaxyz/babyconceptLM-English-matched"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)

The model uses repository-provided custom code, so inspect the pinned revision before enabling trust_remote_code=True in security-sensitive environments.

Intended use

The checkpoint is released for reproducibility of the frozen English matched-control analyses. It should not be substituted for zondaxyz/babyconceptLM-583-en: the two repositories contain different trained weights and use different frozen recipes.