Instructions to use atenareply/smollm2-135m-noval-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atenareply/smollm2-135m-noval-instruct with Transformers:

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

pipe = pipeline("text-generation", model="atenareply/smollm2-135m-noval-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("atenareply/smollm2-135m-noval-instruct")
model = AutoModelForCausalLM.from_pretrained("atenareply/smollm2-135m-noval-instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use atenareply/smollm2-135m-noval-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "atenareply/smollm2-135m-noval-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atenareply/smollm2-135m-noval-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/atenareply/smollm2-135m-noval-instruct

SGLang

How to use atenareply/smollm2-135m-noval-instruct 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 "atenareply/smollm2-135m-noval-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atenareply/smollm2-135m-noval-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "atenareply/smollm2-135m-noval-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atenareply/smollm2-135m-noval-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use atenareply/smollm2-135m-noval-instruct with Docker Model Runner:
```
docker model run hf.co/atenareply/smollm2-135m-noval-instruct
```

SmolLM2-135M Noval — Instruct (SFT)

Instruction-tuned domain assistant: SFT of the 135M CPT model on grounded domain instruction pairs blended with general instructions.

Overview

Stage: SFT (TRL SFTTrainer, ChatML, assistant-only loss)
Lineage: SmolLM2-135M → CPT (noval) → SFT (this model)
Method: SFT from the CPT'd checkpoint. ChatML with a {% generation %} block + assistant-only loss; grounded instruction pairs (teacher-distilled, generator≠judge, verbatim-number grounding filter [genie]) blended 60/40 with smol-smoltalk [collapse].
Domain: fictional — Orbital Mining Corporation (OMC) technical docs + Mars Express telemetry.

Training


Dataset	noval-corp-sft-small — train 1,388 / val 43 (chat `messages`)
LR / epochs	2e-5 cosine, warmup 0.03, 3 epochs, max_len 2048, eff_batch 32

Evaluation

Metric	Value	Note
train_loss	2.257	healthy curve, no overfit
eval_loss	1.946	per-epoch 2.048 → 1.959 → 1.946
token accuracy	0.57	0.47 → 0.57

Eval is a held-out, deterministic verifiable harness (synthetic tasks); baseline = the pre-SFT ParamΔ model. See noval-corp/scripts/eval_agentic.py.

Intended use & limitations

Domain Q&A / summarization / code-explanation over OMC / Mars-Express, in chat (ChatML) format.

Limitations:

135M instruct is intrinsically limited.
Instruction-following eval was handed off externally (no in-repo task metrics).
Fictional domain; sparse one-off entities hallucination-prone.

Innovations tested

Local-subscription teacher distillation — grounded pairs generated by Claude Code (generator ≠ judge), with a rule-based verbatim-number grounding gate [genie].

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("atenareply/smollm2-135m-noval-instruct")
model = AutoModelForCausalLM.from_pretrained("atenareply/smollm2-135m-noval-instruct")
msgs = [{"role": "user", "content": "What does the Orbital Mining Corporation do?"}]
inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)
print(tok.decode(model.generate(**inputs, max_new_tokens=256)[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Citations

GENIE (grounded synthesis) — Mirza et al., ICLR 2024. arXiv:2401.14367
Model collapse (≥50% real data) — Shumailov et al., 2024. arXiv:2404.01413

Card generated by noval-corp/scripts/gen_model_cards.py (standardized across the noval-corp model family).

Downloads last month: 54

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for atenareply/smollm2-135m-noval-instruct

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

(929)

this model

Datasets used to train atenareply/smollm2-135m-noval-instruct

Papers for atenareply/smollm2-135m-noval-instruct

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

Paper • 2404.01413 • Published Apr 1, 2024

Genie: Achieving Human Parity in Content-Grounded Datasets Generation

Paper • 2401.14367 • Published Jan 25, 2024 • 8