Instructions to use sfanm/d24-sft-v1base-olmo3-2.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sfanm/d24-sft-v1base-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-v1base-olmo3-2.3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sfanm/d24-sft-v1base-olmo3-2.3B")
model = AutoModelForCausalLM.from_pretrained("sfanm/d24-sft-v1base-olmo3-2.3B", 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 sfanm/d24-sft-v1base-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-v1base-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-v1base-olmo3-2.3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sfanm/d24-sft-v1base-olmo3-2.3B

SGLang

How to use sfanm/d24-sft-v1base-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-v1base-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-v1base-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-v1base-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-v1base-olmo3-2.3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sfanm/d24-sft-v1base-olmo3-2.3B with Docker Model Runner:
```
docker model run hf.co/sfanm/d24-sft-v1base-olmo3-2.3B
```

sfanm commited on Jun 12

Commit

a9a7a62

verified ·

1 Parent(s): 3595dc0

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +31 -0

README.md ADDED Viewed

	@@ -0,0 +1,31 @@

+---
+license: other
+language: en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- nanochat
+- nemotron
+- from-scratch
+- perlmutter
+- gpt2-tokenizer
+---
+# d24-sft-v1base-olmo3-2.3B
+v1-base SFT chat model, OLMo-3 Dolmino-style midtrain.
+nanochat-style **depth-24** decoder — 24 layers × 1536 hidden × 12 heads, SwiGLU / RoPE / RMSNorm, tied embeddings, GPT-2 BPE vocab (50304), **0.757B params**, 2048-token context.
+**Lineage.** v1 pretrain (5.84B ClimbMix) → OLMo-3 Dolmino-style midtrain (2.3B corpus, 20 components incl. instruction/QA) → SFT (nanochat mix).
+**Metrics.** GSM8K (greedy, full 1319): **4.93%** · SFT val lm-loss 0.222 (overfits SFT train via format familiarity).
+## Load
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+m = "sfanm/d24-sft-v1base-olmo3-2.3B"
+tok = AutoTokenizer.from_pretrained(m)
+model = AutoModelForCausalLM.from_pretrained(m, torch_dtype="bfloat16")
+```
+*Research checkpoint from a from-scratch nanochat-d24 replication (pretrain → midtrain → SFT → RL) on NERSC Perlmutter. Trained on third-party corpora (ClimbMix, FineMath, OpenMath, MetaMath, OpenThoughts, OLMo-3 Dolmino, SmolTalk, …) — see those datasets' licenses; provided as-is for research.*