Instructions to use zycalice/unsloth-olmo3-32B-auto-mlp-0203 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zycalice/unsloth-olmo3-32B-auto-mlp-0203 with Transformers:

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

pipe = pipeline("text-generation", model="zycalice/unsloth-olmo3-32B-auto-mlp-0203")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zycalice/unsloth-olmo3-32B-auto-mlp-0203")
model = AutoModelForCausalLM.from_pretrained("zycalice/unsloth-olmo3-32B-auto-mlp-0203", 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 zycalice/unsloth-olmo3-32B-auto-mlp-0203 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zycalice/unsloth-olmo3-32B-auto-mlp-0203"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zycalice/unsloth-olmo3-32B-auto-mlp-0203",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zycalice/unsloth-olmo3-32B-auto-mlp-0203

SGLang

How to use zycalice/unsloth-olmo3-32B-auto-mlp-0203 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 "zycalice/unsloth-olmo3-32B-auto-mlp-0203" \
    --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": "zycalice/unsloth-olmo3-32B-auto-mlp-0203",
		"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 "zycalice/unsloth-olmo3-32B-auto-mlp-0203" \
        --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": "zycalice/unsloth-olmo3-32B-auto-mlp-0203",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use zycalice/unsloth-olmo3-32B-auto-mlp-0203 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for zycalice/unsloth-olmo3-32B-auto-mlp-0203 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for zycalice/unsloth-olmo3-32B-auto-mlp-0203 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zycalice/unsloth-olmo3-32B-auto-mlp-0203 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="zycalice/unsloth-olmo3-32B-auto-mlp-0203",
    max_seq_length=2048,
)

Docker Model Runner
How to use zycalice/unsloth-olmo3-32B-auto-mlp-0203 with Docker Model Runner:
```
docker model run hf.co/zycalice/unsloth-olmo3-32B-auto-mlp-0203
```

zycalice commited on Feb 10

Commit

556419a

verified ·

1 Parent(s): bfeac46

Upload yz_metadata.json with huggingface_hub

Browse files

Files changed (1) hide show

yz_metadata.json +38 -0

yz_metadata.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+    "model": "unsloth/Olmo-3.1-32B-Instruct",
+    "train_lib":"unsloth",
+    "training_file": "../data/auto_incorrect_train_fix.jsonl",
+    "test_file": null,
+    "finetuned_model_id": "zycalice/unsloth-olmo3-32B-auto-mlp-0203",
+    "max_seq_length": 2048,
+    "load_in_4bit": false,
+    "loss": "sft",
+    "is_peft": true,
+    "target_modules": [
+        "gate_proj",
+        "up_proj",
+        "down_proj"
+    ],
+    "lora_bias": "none",
+    "r": 32,
+    "lora_alpha": 64,
+    "lora_dropout": 0.0,
+    "use_rslora": true,
+    "merge_before_push": true,
+    "push_to_private": false,
+    "epochs": 1,
+    "max_steps": null,
+    "per_device_train_batch_size": 4,
+    "gradient_accumulation_steps": 4,
+    "warmup_steps": 5,
+    "learning_rate": 1.5e-05,
+    "logging_steps": 1,
+    "optim": "adamw_8bit",
+    "weight_decay": 0.01,
+    "lr_scheduler_type": "linear",
+    "seed": 0,
+    "beta": 0.1,
+    "save_steps": 5000,
+    "output_dir": "./tmp_olmo3-32b-auto-mlp-0203",
+    "train_on_responses_only": true
+}