Blame for README.md

---
license: apache-2.0
language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - tiny-lm
  - qwen3
  - value-residual
  - muon
  - knowledge-distillation
  - ablation
datasets:
  - HuggingFaceFW/fineweb-edu
---

# JugnuLM-110M-R4a (value residuals + Muon + logit distillation)

**What "R4a" means.** Rung 4 of the JugnuLM phase-2 ablation ladder — the first
**knowledge-distillation** attempt. We take rung **R2**
([JugnuLM-110M-R2](https://huggingface.co/altslate/JugnuLM-110M-R2), value residuals + Muon)
and add **offline top-k logit distillation** from a teacher, holding data/optimizer/schedule
fixed. This is the **"a" variant** — a deliberately KD-heavy setting; a rebalanced **R4b** follows.

## What changed: logit KD from SmolLM2-1.7B

The frozen teacher **[SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B)** (base;
shares our SmolLM2 tokenizer, 49,152 vocab) was run over ~6B tokens of FineWeb-Edu, storing its
**top-16 next-token logits** per position. The student trains to match that distribution:

> `loss = α·CE + (1−α)·τ²·KL(student ‖ teacher_top16) + z-loss`,  with **α=0.5, τ=2**.

## Result — distillation lifts ARC, but this setting over-weights KD

| 110M rung | BLiMP ↑ | ARC-Easy ↑ | WikiText-2 byte-ppl ↓ |
|---|---|---|---|
| R2 — value residuals + Muon | 80.78 | 56.10 | **1.932** |
| **R4a — + logit KD (α=0.5, τ=2)** | 80.39 | **56.99** | 2.178 |

**ARC-Easy reached 56.99 — the best of any JugnuLM rung, essentially matching GPT-X2-125M's
57.07** — confirming distillation is the right lever for reasoning. **However**, with α=0.5 and
τ=2 the KD term carries ~4× the weight of the hard-label loss, so the student over-imitates the
teacher's softened distribution at the cost of sharp next-token prediction: **WikiText perplexity
rose to 2.178** (from R2's 1.932). On the leaderboard's blended efficiency score this perplexity
regression outweighs the ARC gain, so **R4a is not kept as the ladder base** — but it validates
the lever and motivates the rebalanced **R4b (α=0.7, τ=1)**, which aims to keep the ARC win
without the perplexity damage. Evaluated with EleutherAI `lm-evaluation-harness`.

## ⚠️ Loading — requires `trust_remote_code`

Value residuals are a custom attention pathway; loading as a stock Qwen3 silently drops them.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("altslate/JugnuLM-110M-R4a")
model = AutoModelForCausalLM.from_pretrained("altslate/JugnuLM-110M-R4a", trust_remote_code=True)
ids = tok("The theory of relativity was developed by", return_tensors="pt").input_ids
print(tok.decode(model.generate(ids, max_new_tokens=30, repetition_penalty=1.3)[0], skip_special_tokens=True))
```

## Architecture & training

Identical architecture/optimizer to R2 (value residuals + Muon): Qwen3-arch, **23 layers ×
576**, GQA 9/3, RoPE, SwiGLU, RMSNorm, QK-Norm, tied embeddings, SmolLM2 tokenizer (49,152),
z-loss 1e-4. Trained from scratch on ~8.4B tokens of FineWeb-Edu with the KD loss above, Muon
(peak 2e-2) + AdamW (1.5e-3) on a shared cosine, ~0.5M-token global batch, bf16, DDP on 4× RTX
PRO 4500 Blackwell. Teacher logits precomputed offline (top-16 over a 6B-token region).

## Intended use & limitations

Research **base** model (not instruction-tuned). Best-in-family ARC-Easy reasoning, but higher
perplexity than R1/R2 due to the KD-heavy setting. English-only, occasional repetition. Not for
production. For a more balanced distilled model, see R4b (when released).

## Links

- Base rung: [altslate/JugnuLM-110M-R2](https://huggingface.co/altslate/JugnuLM-110M-R2)
- Teacher: [HuggingFaceTB/SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B)
- Training code & ablation ladder: https://github.com/AltSlate-Labs/jugnu

## Paper

This model is described in [*Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M*](https://arxiv.org/abs/2609.14715)
(arXiv:2609.14715 · [HF Papers](https://huggingface.co/papers/2609.14715)).

```bibtex
@misc{rajput2026jugnu,
  title         = {Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M},
  author        = {Rajput, Dushyant and Chauhan, Nirdesh and Kosaraju, Siddharth},
  year          = {2026},
  eprint        = {2609.14715},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
  url           = {https://arxiv.org/abs/2609.14715}
}
```