Instructions to use altslate/JugnuLM-110M-R4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use altslate/JugnuLM-110M-R4b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="altslate/JugnuLM-110M-R4b", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("altslate/JugnuLM-110M-R4b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use altslate/JugnuLM-110M-R4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "altslate/JugnuLM-110M-R4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "altslate/JugnuLM-110M-R4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/altslate/JugnuLM-110M-R4b

SGLang

How to use altslate/JugnuLM-110M-R4b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "altslate/JugnuLM-110M-R4b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "altslate/JugnuLM-110M-R4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "altslate/JugnuLM-110M-R4b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "altslate/JugnuLM-110M-R4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use altslate/JugnuLM-110M-R4b with Docker Model Runner:
```
docker model run hf.co/altslate/JugnuLM-110M-R4b
```

JugnuLM-110M-R4b / README.md

rajpdus

Model card: cite arXiv:2609.14715

de9534d verified 22 days ago

preview code

Raw History Blame Contribute Delete

4.26 kB

---
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-R4b (rebalanced logit distillation)

**What "R4b" means.** The rebalanced counterpart of
[JugnuLM-110M-R4a](https://huggingface.co/altslate/JugnuLM-110M-R4a). Same offline top-16 logit
distillation from **SmolLM2-1.7B**, but with the KD term **dialed down** to stop it dominating:

> `loss = α·CE + (1−α)·τ²·KL(student ‖ teacher_top16) + z-loss`
> **R4a: α=0.5, τ=2 (KD ≈4× CE)  →  R4b: α=0.7, τ=1 (KD ≈0.4× CE)**
R4b was run to test whether a gentler KD keeps R4a's ARC-Easy gain **without** its perplexity
collapse. **It does not** — an honest negative.
## Result — the rebalance fixed perplexity but lost the ARC gain
| 110M rung | BLiMP ↑ | ARC-Easy ↑ | WikiText-2 byte-ppl ↓ |
|---|---|---|---|
| R2 — value residuals + Muon (base) | **80.78** | **56.10** | 1.932 |
| R4a — + KD, heavy (α=0.5, τ=2) | 80.39 | **56.99** | 2.178 |
| **R4b — + KD, light (α=0.7, τ=1)** | 79.30 | 55.47 | **1.9165** |
**R4b recovers R2-level perplexity (1.9165, best of the three), but ARC-Easy falls to 55.47 —
*below* the no-KD R2 baseline (56.10) — and BLiMP drops to 79.30.** So R4b is worse than R2 on
BLiMP, ARC, and the blended efficiency score; **it is not kept.** Together R4a/R4b bracket a
narrow, unfriendly KD operating point: **heavy KD buys ARC but wrecks perplexity; light KD fixes
perplexity but loses the ARC benefit.** Offline logit KD from a 1.7B teacher (≈15× the student)
did not yield a *keepable* win at this 8.4B-token scale.
*Caveat / confound:* R4a and R4b trained on the **6B-token KD region** (the span with precomputed
teacher logits), whereas R2 sampled the full ~10B FineWeb-Edu pool — so the KD runs saw less
unique data, which likely contributed to R4b's BLiMP drop independent of the KD change. A fair KD
comparison would precompute teacher logits over the full corpus. Evaluated with EleutherAI
`lm-evaluation-harness`.
## ⚠️ Loading — requires `trust_remote_code`
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("altslate/JugnuLM-110M-R4b")
model = AutoModelForCausalLM.from_pretrained("altslate/JugnuLM-110M-R4b", 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 to R4a except the KD weights (α=0.7, τ=1): Qwen3-arch + value residuals, **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 over the 6B-token KD region, 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.
## Intended use & limitations
Research **base** model, published as an ablation record. **For actual use prefer
[JugnuLM-110M-R2](https://huggingface.co/altslate/JugnuLM-110M-R2)** (better BLiMP + ARC) or
[R4a](https://huggingface.co/altslate/JugnuLM-110M-R4a) (best ARC-Easy). English-only. Not for
production.
## Links
- Base rung / recommended: [altslate/JugnuLM-110M-R2](https://huggingface.co/altslate/JugnuLM-110M-R2)
- Heavy-KD counterpart: [altslate/JugnuLM-110M-R4a](https://huggingface.co/altslate/JugnuLM-110M-R4a)
- 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}
}
```

	---
	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-R4b (rebalanced logit distillation)

	What "R4b" means. The rebalanced counterpart of
	[JugnuLM-110M-R4a](https://huggingface.co/altslate/JugnuLM-110M-R4a). Same offline top-16 logit
	distillation from SmolLM2-1.7B, but with the KD term dialed down to stop it dominating:

	> `loss = α·CE + (1−α)·τ²·KL(student ‖ teacher_top16) + z-loss`
	> R4a: α=0.5, τ=2 (KD ≈4× CE) → R4b: α=0.7, τ=1 (KD ≈0.4× CE)

	R4b was run to test whether a gentler KD keeps R4a's ARC-Easy gain without its perplexity
	collapse. It does not — an honest negative.

	## Result — the rebalance fixed perplexity but lost the ARC gain

	\| 110M rung \| BLiMP ↑ \| ARC-Easy ↑ \| WikiText-2 byte-ppl ↓ \|
	\|---\|---\|---\|---\|
	\| R2 — value residuals + Muon (base) \| 80.78 \| 56.10 \| 1.932 \|
	\| R4a — + KD, heavy (α=0.5, τ=2) \| 80.39 \| 56.99 \| 2.178 \|
	\| R4b — + KD, light (α=0.7, τ=1) \| 79.30 \| 55.47 \| 1.9165 \|

	**R4b recovers R2-level perplexity (1.9165, best of the three), but ARC-Easy falls to 55.47 —
	below the no-KD R2 baseline (56.10) — and BLiMP drops to 79.30.** So R4b is worse than R2 on
	BLiMP, ARC, and the blended efficiency score; it is not kept. Together R4a/R4b bracket a
	narrow, unfriendly KD operating point: **heavy KD buys ARC but wrecks perplexity; light KD fixes
	perplexity but loses the ARC benefit.** Offline logit KD from a 1.7B teacher (≈15× the student)
	did not yield a keepable win at this 8.4B-token scale.

	Caveat / confound: R4a and R4b trained on the 6B-token KD region (the span with precomputed
	teacher logits), whereas R2 sampled the full ~10B FineWeb-Edu pool — so the KD runs saw less
	unique data, which likely contributed to R4b's BLiMP drop independent of the KD change. A fair KD
	comparison would precompute teacher logits over the full corpus. Evaluated with EleutherAI
	`lm-evaluation-harness`.

	## ⚠️ Loading — requires `trust_remote_code`

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("altslate/JugnuLM-110M-R4b")
	model = AutoModelForCausalLM.from_pretrained("altslate/JugnuLM-110M-R4b", 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 to R4a except the KD weights (α=0.7, τ=1): Qwen3-arch + value residuals, **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 over the 6B-token KD region, 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.

	## Intended use & limitations

	Research base model, published as an ablation record. **For actual use prefer
	[JugnuLM-110M-R2](https://huggingface.co/altslate/JugnuLM-110M-R2)** (better BLiMP + ARC) or
	[R4a](https://huggingface.co/altslate/JugnuLM-110M-R4a) (best ARC-Easy). English-only. Not for
	production.

	## Links

	- Base rung / recommended: [altslate/JugnuLM-110M-R2](https://huggingface.co/altslate/JugnuLM-110M-R2)
	- Heavy-KD counterpart: [altslate/JugnuLM-110M-R4a](https://huggingface.co/altslate/JugnuLM-110M-R4a)
	- 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}
	}
	```