Instructions to use uaytug/ucoder-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uaytug/ucoder-mini with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uaytug/ucoder-mini")
model = AutoModelForCausalLM.from_pretrained("uaytug/ucoder-mini")
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

vLLM

How to use uaytug/ucoder-mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/uaytug/ucoder-mini

SGLang

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

Docker Model Runner
How to use uaytug/ucoder-mini with Docker Model Runner:
```
docker model run hf.co/uaytug/ucoder-mini
```

uaytug commited on Jan 6

Commit

e6b9ffd

verified ·

1 Parent(s): 47e99e0

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -195,7 +195,7 @@ def quickselect(nums, k):
 </details>
 <details>
-<summary><b>📐 Mathematical Reasoning</b></summary>
 **Prompt:** Prove that the sum of the first n odd numbers equals n².
@@ -223,7 +223,7 @@ Sum = n × (first + last) / 2 = n × (1 + 2n - 1) / 2 = n × 2n / 2 = n²
 </details>
 <details>
-<summary><b>🐛 Debugging</b></summary>
 **Prompt:** Why does this code give wrong results?
 ```python

 </details>
 <details>
+<summary><b>Mathematical Reasoning</b></summary>
 **Prompt:** Prove that the sum of the first n odd numbers equals n².
 </details>
 <details>
+<summary><b>Debugging</b></summary>
 **Prompt:** Why does this code give wrong results?
 ```python