Instructions to use devZeeshaan/NanoR1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use devZeeshaan/NanoR1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "devZeeshaan/NanoR1")

Transformers

How to use devZeeshaan/NanoR1 with Transformers:

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

pipe = pipeline("text-generation", model="devZeeshaan/NanoR1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("devZeeshaan/NanoR1")
model = AutoModelForCausalLM.from_pretrained("devZeeshaan/NanoR1", 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 devZeeshaan/NanoR1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "devZeeshaan/NanoR1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "devZeeshaan/NanoR1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/devZeeshaan/NanoR1

SGLang

How to use devZeeshaan/NanoR1 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 "devZeeshaan/NanoR1" \
    --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": "devZeeshaan/NanoR1",
		"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 "devZeeshaan/NanoR1" \
        --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": "devZeeshaan/NanoR1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use devZeeshaan/NanoR1 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 devZeeshaan/NanoR1 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 devZeeshaan/NanoR1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for devZeeshaan/NanoR1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="devZeeshaan/NanoR1",
    max_seq_length=2048,
)

Docker Model Runner
How to use devZeeshaan/NanoR1 with Docker Model Runner:
```
docker model run hf.co/devZeeshaan/NanoR1
```

devZeeshaan commited on Mar 16, 2025

Commit

2c89e96

verified ·

1 Parent(s): 22d74d4

Update config.json

Browse files

Files changed (1) hide show

config.json +44 -0

config.json CHANGED Viewed

	@@ -0,0 +1,44 @@

+{
+  "_name_or_path": "unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit",
+  "architectures": ["Qwen2ForCausalLM"],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.2.15",
+  "use_cache": true,
+  "vocab_size": 151936,
+  "quantization": {
+    "load_in_4bit": true
+  },
+  "lora": {
+    "init_lora_weights": true,
+    "lora_alpha": 64,
+    "lora_bias": false,
+    "lora_dropout": 0,
+    "target_modules": [
+      "up_proj",
+      "o_proj",
+      "q_proj",
+      "gate_proj",
+      "v_proj",
+      "k_proj",
+      "down_proj"
+    ]
+  }
+}