Instructions to use azzzacs/LogicCoder-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use azzzacs/LogicCoder-7B with Transformers:

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

pipe = pipeline("text-generation", model="azzzacs/LogicCoder-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("azzzacs/LogicCoder-7B")
model = AutoModelForCausalLM.from_pretrained("azzzacs/LogicCoder-7B")
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-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "azzzacs/LogicCoder-7B"
# 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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/azzzacs/LogicCoder-7B

SGLang

How to use azzzacs/LogicCoder-7B 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-7B" \
    --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-7B",
		"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-7B" \
        --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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use azzzacs/LogicCoder-7B with Docker Model Runner:
```
docker model run hf.co/azzzacs/LogicCoder-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Paper Page

Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal.

LogicCoder-7B

LogicCoder-7B is a 7B-parameter language model fine-tuned for code generation tasks. It is based on the DeepSeek-R1-Distill-Qwen-7B model and trained on a Python subset of the open-r1/codeforces-cots dataset.

This model was fine-tuned on pruned CoTs examples derived via our ASAP method(Anchor-guided, Surprisal-polished Pruning), focusing on highly compressed yet semantically informative reasoning traces.

GitHub Repository: https://github.com/Zengwh02/ASAP

🧠 Reasoning Mode

We recommend explicitly activating reasoning mode by inserting <think> in the prompt.

🔧 Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("azzzacs/LogicCoder-7B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("azzzacs/LogicCoder-7B", 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)

outputs = model.generate(
    model_inputs.input_ids,
    max_new_tokens=4096,
    do_sample=False,
    eos_token_id=tokenizer.eos_token_id
)

print(tokenizer.decode(outputs[0][len(model_inputs.input_ids[0]):], skip_special_tokens=False))

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for azzzacs/LogicCoder-7B

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Finetuned

(303)

this model

Quantizations

2 models

Dataset used to train azzzacs/LogicCoder-7B

Paper for azzzacs/LogicCoder-7B

Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal

Paper • 2508.05988 • Published Aug 8, 2025 • 22