Instructions to use Shekswess/trlm-135m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shekswess/trlm-135m with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Shekswess/trlm-135m")
model = AutoModelForCausalLM.from_pretrained("Shekswess/trlm-135m")
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

vLLM

How to use Shekswess/trlm-135m with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Shekswess/trlm-135m

SGLang

How to use Shekswess/trlm-135m 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 "Shekswess/trlm-135m" \
    --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": "Shekswess/trlm-135m",
		"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 "Shekswess/trlm-135m" \
        --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": "Shekswess/trlm-135m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Shekswess/trlm-135m with Docker Model Runner:
```
docker model run hf.co/Shekswess/trlm-135m
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Tiny Reasoning Language Model (trlm-135)

Model Summary
Post-Training Pipeline
How to use
Training
Evaluation
Limitations
Acknowledgements
License

Model Summary

The Tiny Reasoning Language Model (trlm-135) is a 135M parameter research prototype designed to study how small models can learn step-by-step reasoning. It was built on top of SmolLM2-135M-Instruct and fine-tuned through a 3-stage pipeline:

Stage 1 SFT: general instruction tuning (non-reasoning).
Stage 2 SFT: reasoning traces with <think> tags.
Stage 3 DPO: preference alignment for reasoning style.

The code for everything can be found here

Post-Training Pipeline

How to use

pip install -U transformers accelerate

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Shekswess/trlm-135m"
device = "cuda"  # or "cpu"

# Load tokenizer & model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
).to(device)

# Example prompt
prompt = "Give me a brief explanation of gravity in simple terms."
messages = [
    {"role": "user", "content": prompt}
]

# Apply chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

For reasoning-heavy tasks, set temperature=0.6 and top_p=0.95.

Training

Model

Architecture: Decoder-only transformer (SmolLM2 backbone which infact is Llama 3 based model).
Parameters: ~135M.
Precision: mix-precision (bfloat16) during training.

Software & Hardware

Training Frameworks: PyTorch (ROCm), Hugging Face Transformers & TRL.
Hardware: AMD MI300X (192GB VRAM, 224GB RAM).

Special thanks to @HotAisle

Training Stages

Stage 1 – SFT (non-reasoning)
- ~58k samples, everyday conversations & instruction following.
Stage 2 – SFT (reasoning)
- ~78k samples with <think> segments.
Stage 3 – DPO (alignment)
- ~50k preference pairs (chosen vs. rejected reasoning traces).

Evaluation

Evaluation was done with lm-eval-harness:

Benchmark	Tiny Reasoning Language Model (trlm-135M)	SmolLM2-135M-Instruct	Improvements
ARC Challenge	40.61 (avg)	37.3 (avg)	+3.31
BBH	36.80 (3-shot)	28.2 (3-shot)	+8.6
BoolQ	62.17	–	N/A
GSM8K	2.59 (5-shot)	1.4 (5-shot)	+1.19
IFEval	35.49 (avg)	29.9 (avg)	+5.59
MMLU	34.95	29.3	+5.65
PIQA	64.91	66.3	–1.39
HellaSwag	–	40.9	N/A
MT-Bench	–	19.8	N/A

Limitations

Not production-ready: hallucinations and logical errors are frequent.
Small size: limited general knowledge and reasoning depth.
English-only: multilingual capabilities not explored.

Acknowledgements

@HotAisle for providing the compute resources to train all three stages on a awesome AMD MI300x setup.
@mkurman88 for ideas, feedback and code samples.
HuggingFaceTB team for SmolLM2-135M-Instruct model and the Smoltalk2 dataset collection.
@scottgeng00 for the OLmO-3-Preference-Mix-Deltas dataset.
@eliebakouchi for help with the tokenization.