Instructions to use altslate/JugnuLM-110M-R4a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use altslate/JugnuLM-110M-R4a with Transformers:

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

pipe = pipeline("text-generation", model="altslate/JugnuLM-110M-R4a", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("altslate/JugnuLM-110M-R4a", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use altslate/JugnuLM-110M-R4a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "altslate/JugnuLM-110M-R4a"
# 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-R4a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/altslate/JugnuLM-110M-R4a

SGLang

How to use altslate/JugnuLM-110M-R4a 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-R4a" \
    --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-R4a",
		"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-R4a" \
        --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-R4a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use altslate/JugnuLM-110M-R4a with Docker Model Runner:
```
docker model run hf.co/altslate/JugnuLM-110M-R4a
```

JugnuLM-110M-R4a / README.md

rajpdus

Model card: cite arXiv:2609.14715

4a3deb5 verified 15 days ago

preview code

Raw History Blame Contribute Delete

4.45 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-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}
}
```

	---
	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}
	}
	```