Instructions to use sfanm/d24-sft-v2-olmo3-2.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sfanm/d24-sft-v2-olmo3-2.3B with Transformers:

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

pipe = pipeline("text-generation", model="sfanm/d24-sft-v2-olmo3-2.3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("sfanm/d24-sft-v2-olmo3-2.3B")
model = AutoModelForMultimodalLM.from_pretrained("sfanm/d24-sft-v2-olmo3-2.3B")
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 sfanm/d24-sft-v2-olmo3-2.3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sfanm/d24-sft-v2-olmo3-2.3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sfanm/d24-sft-v2-olmo3-2.3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sfanm/d24-sft-v2-olmo3-2.3B

SGLang

How to use sfanm/d24-sft-v2-olmo3-2.3B 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 "sfanm/d24-sft-v2-olmo3-2.3B" \
    --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": "sfanm/d24-sft-v2-olmo3-2.3B",
		"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 "sfanm/d24-sft-v2-olmo3-2.3B" \
        --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": "sfanm/d24-sft-v2-olmo3-2.3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sfanm/d24-sft-v2-olmo3-2.3B with Docker Model Runner:
```
docker model run hf.co/sfanm/d24-sft-v2-olmo3-2.3B
```

d24 SFT - v2 base + OLMo-3 midtrain (0.757B)

nanochat-style depth-24 decoder (24L x 1536 hidden x 12 heads, SwiGLU / RoPE / RMSNorm, tied embeddings, GPT-2 BPE vocab 50304, 0.757B params, 2048 ctx, LlamaForCausalLM).

Lineage: v2 pretrain (13.1B ClimbMix, WSD) -> OLMo-3 Dolmino-style midtrain (2.245B tok, 1 epoch, sfanm/d24-midtrain-olmo3) -> SFT (nanochat chat mix, 1 epoch, sfanm/d24-sft-mixture).

Eval (greedy, full sets): GSM8K 3.79% | MMLU 32.8% | ARC 35.6%. The OLMo-3 midtrain trades math for general knowledge: MMLU/ARC are notably stronger than the math-heavy d24 variants (~27%), while GSM8K is lower than the reasoning-midtrain SFT (9.86%).

Chat format: ChatML (<|im_start|>role\n...<|im_end|>); see chat_template.jinja.

Downloads last month: 16

Safetensors

Model size

0.8B params

Tensor type

BF16