Instructions to use alpha-ai/llama-3.2-3B-Reason-Reflect-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alpha-ai/llama-3.2-3B-Reason-Reflect-Lite with Transformers:

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

pipe = pipeline("text-generation", model="alpha-ai/llama-3.2-3B-Reason-Reflect-Lite")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alpha-ai/llama-3.2-3B-Reason-Reflect-Lite")
model = AutoModelForCausalLM.from_pretrained("alpha-ai/llama-3.2-3B-Reason-Reflect-Lite", 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 alpha-ai/llama-3.2-3B-Reason-Reflect-Lite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alpha-ai/llama-3.2-3B-Reason-Reflect-Lite"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alpha-ai/llama-3.2-3B-Reason-Reflect-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alpha-ai/llama-3.2-3B-Reason-Reflect-Lite

SGLang

How to use alpha-ai/llama-3.2-3B-Reason-Reflect-Lite 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 "alpha-ai/llama-3.2-3B-Reason-Reflect-Lite" \
    --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": "alpha-ai/llama-3.2-3B-Reason-Reflect-Lite",
		"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 "alpha-ai/llama-3.2-3B-Reason-Reflect-Lite" \
        --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": "alpha-ai/llama-3.2-3B-Reason-Reflect-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alpha-ai/llama-3.2-3B-Reason-Reflect-Lite with Docker Model Runner:
```
docker model run hf.co/alpha-ai/llama-3.2-3B-Reason-Reflect-Lite
```

alphaaico commited on Feb 26, 2025

Commit

d1d6eb1

verified ·

1 Parent(s): 5296ca9

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -1

README.md CHANGED Viewed

@@ -16,8 +16,17 @@ language:
 - en
 datasets:
 - openai/gsm8k
 ---
 # Uploaded Model
 - **Developed by:** alphaaico
@@ -119,4 +128,4 @@ print("Model converted to safetensors successfully.")
 ```
 Alternatively, you can use our GGUF models, which are optimized for inference with llama.cpp, exllama, and other efficient runtimes. GGUF provides better performance on CPU/GPU and is a more portable option for deployment.
-Choose the format that best suits your security, performance, and deployment needs.

 - en
 datasets:
 - openai/gsm8k
+pipeline_tag: text-generation
 ---
+<div align="center">
+<img src="https://cdn-uploads.huggingface.co/production/uploads/669777597cb32718c20d97e9/4emWK_PB-RrifIbrCUjE8.png"
+     alt="Title card"
+     style="width: 500px;
+            height: auto;
+            object-position: center top;">
+</div>
 # Uploaded Model
 - **Developed by:** alphaaico
 ```
 Alternatively, you can use our GGUF models, which are optimized for inference with llama.cpp, exllama, and other efficient runtimes. GGUF provides better performance on CPU/GPU and is a more portable option for deployment.
+Choose the format that best suits your security, performance, and deployment needs.