littlelearner / unfiltered-5b-base

unfiltered-5b-base

5B unbounded base model (pretraining only). The 5B control for the K-5 boundary study.

Part of the LittleLearner scale-up study ( pedagogically-controlled knowledge exposure ): Qwen3 dense LMs trained on a corpus filtered to U.S. K-5 material ( bounded ) vs an unfiltered FineWeb-Edu corpus ( unbounded ), to measure what an interpretable knowledge boundary costs and grants.

Model

• Architecture: Qwen3 dense ( Qwen3ForCausalLM ).
• Size: 5.04B params, hidden 3072, 44 layers, 24 query / 8 KV heads, FFN 9216. Context: 4096.
• Tokenizer: custom 64k byte-level BPE with per-digit splitting (ChatML special tokens).
• Pretraining: 88B tokens on unfiltered FineWeb-Edu (score >= 2, no grade filter). WSD schedule, sharded Muon, MXFP8, Megatron-Core on 8xB200.

Evaluation

• BPB on K-5-domain eval text: 0.644 (vs the bounded 5B's 0.536; the unbounded model is broader).

Usage

# transformers (completion)
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "manueldeprada/littlelearner-5b-unbounded-base"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="cuda")
ids = tok("The sum of 2 and 3 is", return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**ids)[0], skip_special_tokens=True))

# vLLM
from vllm import LLM
llm = LLM("manueldeprada/littlelearner-5b-unbounded-base")
print(llm.generate(["The sum of 2 and 3 is"])[0].outputs[0].text)