Instructions to use gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct

SGLang

How to use gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct 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 "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct" \
    --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": "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct",
		"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 "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct" \
        --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": "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct with Docker Model Runner:
```
docker model run hf.co/gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct
```

Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct

Qwen/Qwen2.5-Coder-3B-Instruct distilled from Qwen/Qwen2.5-Coder-32B-Instruct with Ask to Distill.

Ask to Distill trains a question generator with RL so that the questions it writes expose bounded, learnable token-level disagreement between a teacher and a student on the student's own solutions (the same signal on-policy distillation learns from). A question bank is then sampled from the generator, filtered and deduplicated, and the student is trained with on-policy distillation (OPD) on it. No real training questions and no reference answers are used.

Training


Student	Qwen/Qwen2.5-Coder-3B-Instruct
Teacher	Qwen/Qwen2.5-Coder-32B-Instruct
Question bank	gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct
OPD objective	per-token reverse KL on the student's top-16 tokens, weighted by renormalised student probabilities; no outcome reward
OPD recipe	lr 1e-6 (constant), AdamW, rollout temperature 1.0, fp32 master weights / bf16 compute

Results

LiveCodeBench v5_v6	MBPP+	APPS-Intro	APPS-Interview	APPS-Comp	CodeContests	Avg
17.0	65.1	31.6	7.6	3.7	2.4	21.2

LiveCodeBench v5_v6 (342 problems, n=4, pass@1); MBPP+ (EvalPlus, greedy, lenient answer extraction); APPS intro / interview (1k subset) / competition and CodeContests test (165): n=1, temperature 0.2, top-p 0.95, top-k 20, 4,096 tokens, at most 50 tests per problem. Avg = mean of six.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
repo = "gasolsun/Code_Qwen2.5-Coder-3B-Instruct_Qwen2.5-Coder-32B-Instruct"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "..."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=4096, do_sample=True, temperature=0.7, top_p=0.95)
print(tok.decode(out[0, inputs.shape[1]:], skip_special_tokens=True))