Instructions to use azzzacs/LogicCoder-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use azzzacs/LogicCoder-8B with Transformers:

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

pipe = pipeline("text-generation", model="azzzacs/LogicCoder-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("azzzacs/LogicCoder-8B")
model = AutoModelForCausalLM.from_pretrained("azzzacs/LogicCoder-8B")
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 azzzacs/LogicCoder-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "azzzacs/LogicCoder-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "azzzacs/LogicCoder-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/azzzacs/LogicCoder-8B

SGLang

How to use azzzacs/LogicCoder-8B 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 "azzzacs/LogicCoder-8B" \
    --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": "azzzacs/LogicCoder-8B",
		"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 "azzzacs/LogicCoder-8B" \
        --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": "azzzacs/LogicCoder-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use azzzacs/LogicCoder-8B with Docker Model Runner:
```
docker model run hf.co/azzzacs/LogicCoder-8B
```

nielsr HF Staff commited on Aug 17, 2025

Commit

68caf65

verified ·

1 Parent(s): 6debec4

Improve model card: Add pipeline tag, library name, and GitHub link

Browse files

This PR enhances the model card by:
- Adding the `pipeline_tag: text-generation` to ensure better discoverability on the Hub (https://huggingface.co/models?pipeline_tag=text-generation).
- Specifying the `library_name: transformers` to indicate compatibility with the Hugging Face Transformers library.
- Including a direct link to the GitHub repository (https://github.com/azzzacs/ASAP) for easy access to the code.

Please review and merge this PR.

Files changed (1) hide show

README.md +12 -5

README.md CHANGED Viewed

@@ -1,11 +1,13 @@
 ---
-license: mit
-datasets:
-- open-r1/codeforces-cots
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 tags:
 - code
 ---
 # Paper Page
@@ -18,6 +20,9 @@ tags:
 This model was fine-tuned on pruned CoTs examples derived via our **ASAP** method(**A**nchor-guided, **S**urpris**a**l-polished **P**runing), focusing on highly compressed yet semantically informative reasoning traces.
 # 🧠 Reasoning Mode
 We recommend **explicitly activating reasoning mode by inserting ```<think>``` in the prompt**.
@@ -30,8 +35,10 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("azzzacs/LogicCoder-8B", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("azzzacs/LogicCoder-8B", device_map="auto", trust_remote_code=True).eval()
-message = [{"role": "user", "content": "Please write a Python quick sort algorithm.\n"}]
-prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False) + "<｜Assistant｜><think>\n"
 model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)

 ---
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+datasets:
+- open-r1/codeforces-cots
+license: mit
 tags:
 - code
+pipeline_tag: text-generation
+library_name: transformers
 ---
 # Paper Page
 This model was fine-tuned on pruned CoTs examples derived via our **ASAP** method(**A**nchor-guided, **S**urpris**a**l-polished **P**runing), focusing on highly compressed yet semantically informative reasoning traces.
+## Code
+For the official implementation, please refer to the [ASAP GitHub repository](https://github.com/azzzacs/ASAP).
 # 🧠 Reasoning Mode
 We recommend **explicitly activating reasoning mode by inserting ```<think>``` in the prompt**.
 tokenizer = AutoTokenizer.from_pretrained("azzzacs/LogicCoder-8B", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("azzzacs/LogicCoder-8B", device_map="auto", trust_remote_code=True).eval()
+message = [{"role": "user", "content": "Please write a Python quick sort algorithm.
+"}]
+prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False) + "<｜Assistant｜><think>
+"
 model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)