Instructions to use kd13/Coder-o1-mini-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kd13/Coder-o1-mini-reasoning with Transformers:

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

pipe = pipeline("text-generation", model="kd13/Coder-o1-mini-reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kd13/Coder-o1-mini-reasoning")
model = AutoModelForCausalLM.from_pretrained("kd13/Coder-o1-mini-reasoning")
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 kd13/Coder-o1-mini-reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kd13/Coder-o1-mini-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kd13/Coder-o1-mini-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kd13/Coder-o1-mini-reasoning

SGLang

How to use kd13/Coder-o1-mini-reasoning 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 "kd13/Coder-o1-mini-reasoning" \
    --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": "kd13/Coder-o1-mini-reasoning",
		"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 "kd13/Coder-o1-mini-reasoning" \
        --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": "kd13/Coder-o1-mini-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kd13/Coder-o1-mini-reasoning with Docker Model Runner:
```
docker model run hf.co/kd13/Coder-o1-mini-reasoning
```

kd13 commited on 25 days ago

Commit

3a137e3

verified ·

1 Parent(s): 57bf074

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -25

README.md CHANGED Viewed

@@ -1,27 +1,3 @@
 ---
 license: apache-2.0
-base_model: kd13/mua-o1-pro-stage2
-tags:
-  - qwen2.5
-  - lora-merged
-  - reasoning
-  - python
-  - mua-o1-pro
----
-# MUA o1 Pro — Stage 3 (merged)
-Stage 3 reasoning-specialized model from **OumuamuaAI**, fine-tuned from `kd13/mua-o1-pro-stage2`
-(itself fine-tuned from Qwen2.5-Coder-1.5B). Stage 3 was a LoRA reasoning stage (ChatML, `<think>` reasoning
-inside the assistant turn, plus tool-calling), merged into the base weights here.
-## Format
-ChatML with roles: `system -> developer -> user -> assistant`. Reasoning appears as a `<think>...</think>`
-block at the start of the assistant turn when the task needs it. Use the bundled chat template.
-## Usage
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-tok = AutoTokenizer.from_pretrained("kd13/Coder-o1-mini")
-model = AutoModelForCausalLM.from_pretrained("kd13/Coder-o1-mini", torch_dtype="float16", device_map="auto")
-```

 ---
 license: apache-2.0
+---