Instructions to use nirusanan/Qwen2.5-1.5B-NextJs-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nirusanan/Qwen2.5-1.5B-NextJs-code with Transformers:

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

pipe = pipeline("text-generation", model="nirusanan/Qwen2.5-1.5B-NextJs-code")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nirusanan/Qwen2.5-1.5B-NextJs-code")
model = AutoModelForCausalLM.from_pretrained("nirusanan/Qwen2.5-1.5B-NextJs-code")
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 nirusanan/Qwen2.5-1.5B-NextJs-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nirusanan/Qwen2.5-1.5B-NextJs-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nirusanan/Qwen2.5-1.5B-NextJs-code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nirusanan/Qwen2.5-1.5B-NextJs-code

SGLang

How to use nirusanan/Qwen2.5-1.5B-NextJs-code 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 "nirusanan/Qwen2.5-1.5B-NextJs-code" \
    --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": "nirusanan/Qwen2.5-1.5B-NextJs-code",
		"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 "nirusanan/Qwen2.5-1.5B-NextJs-code" \
        --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": "nirusanan/Qwen2.5-1.5B-NextJs-code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nirusanan/Qwen2.5-1.5B-NextJs-code with Docker Model Runner:
```
docker model run hf.co/nirusanan/Qwen2.5-1.5B-NextJs-code
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Information

The Qwen2.5-1.5B-NextJs-code is a quantized, fine-tuned version of the Qwen2.5-1.5B-Instruct model designed specifically for generating NextJs code.

Base model: Qwen/Qwen2.5-1.5B-Instruct

How to use

Starting with transformers version 4.44.0 and later, you can run conversational inference using the Transformers pipeline.

Make sure to update your transformers installation via pip install --upgrade transformers.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

def get_pipline():
    model_name = "nirusanan/Qwen2.5-1.5B-NextJs-code"

    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
    tokenizer.pad_token = tokenizer.eos_token

    model = AutoModelForCausalLM.from_pretrained(
        model_name,
        torch_dtype=torch.float16,
        device_map="cuda:0",
        trust_remote_code=True
    )

    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=3500)

    return pipe

pipe = get_pipline()

def generate_prompt(project_title, description):
    prompt = f"""Below is an instruction that describes a project. Write Nextjs 14 code to accomplish the project described below.

### Instruction:
Project:
{project_title}

Project Description:
{description}

### Response:
"""
    return prompt

prompt = generate_prompt(project_title = "Your NextJs project", description = "Your NextJs project description")
result = pipe(prompt)
generated_text = result[0]['generated_text']
print(generated_text.split("### End")[0])

Downloads last month: 19

Safetensors

Model size

2B params

Tensor type

F16

Model tree for nirusanan/Qwen2.5-1.5B-NextJs-code

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

(1553)

this model

Merges

1 model

Quantizations

2 models