Spaces:
Running
on
Zero
Running
on
Zero
| import gradio as gr | |
| import torch | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| import spaces | |
| title = """# 🙋🏻♂️Welcome to 🌟Tonic's ☯️🧑💻Yi-Coder-9B-Chat Demo!""" | |
| description = """Yi-Coder-9B-Chat is a 9B parameter model fine-tuned for coding tasks. This demo showcases its ability to generate code based on your prompts. Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters. Excelling in long-context understanding with a maximum context length of 128K tokens. - Supporting 52 major programming languages: | |
| ```bash | |
| 'java', 'markdown', 'python', 'php', 'javascript', 'c++', 'c#', 'c', 'typescript', 'html', 'go', 'java_server_pages', 'dart', 'objective-c', 'kotlin', 'tex', 'swift', 'ruby', 'sql', 'rust', 'css', 'yaml', 'matlab', 'lua', 'json', 'shell', 'visual_basic', 'scala', 'rmarkdown', 'pascal', 'fortran', 'haskell', 'assembly', 'perl', 'julia', 'cmake', 'groovy', 'ocaml', 'powershell', 'elixir', 'clojure', 'makefile', 'coffeescript', 'erlang', 'lisp', 'toml', 'batchfile', 'cobol', 'dockerfile', 'r', 'prolog', 'verilog' | |
| ``` | |
| ### Join us : | |
| 🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [](https://discord.gg/qdfnvSPcqP) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Build Tonic](https://git.tonic-ai.com/contribute)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗 | |
| """ | |
| # Define the device and model path | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| model_path = "01-ai/Yi-Coder-9B-Chat" | |
| # Load the tokenizer and model | |
| tokenizer = AutoTokenizer.from_pretrained(model_path) | |
| model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto").eval() | |
| def generate_code(system_prompt, user_prompt, max_length): | |
| messages = [ | |
| {"role": "system", "content": system_prompt}, | |
| {"role": "user", "content": user_prompt} | |
| ] | |
| text = tokenizer.apply_chat_template( | |
| messages, | |
| tokenize=False, | |
| add_generation_prompt=True | |
| ) | |
| model_inputs = tokenizer([text], return_tensors="pt").to(device) | |
| generated_ids = model.generate( | |
| model_inputs.input_ids, | |
| max_new_tokens=max_length, | |
| eos_token_id=tokenizer.eos_token_id | |
| ) | |
| generated_ids = [ | |
| output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) | |
| ] | |
| response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| return response | |
| def gradio_interface(): | |
| with gr.Blocks() as interface: | |
| gr.Markdown(title) | |
| gr.Markdown(description) | |
| system_prompt_input = gr.Textbox( | |
| label="☯️Yinstruction:", | |
| value="You are a helpful coding assistant. Provide clear and concise code examples.", | |
| lines=2 | |
| ) | |
| user_prompt_input = gr.Code( | |
| label="🤔Coding Question", | |
| value="Write a quick sort algorithm in Python.", | |
| language="python", | |
| lines=15 | |
| ) | |
| code_output = gr.Code(label="☯️Yi-Coder-7B", language='python', lines=20, interactive=True) | |
| max_length_slider = gr.Slider(minimum=1, maximum=1800, value=650, label="Max Token Length") | |
| generate_button = gr.Button("Generate Code") | |
| generate_button.click( | |
| generate_code, | |
| inputs=[system_prompt_input, user_prompt_input, max_length_slider], | |
| outputs=code_output | |
| ) | |
| return interface | |
| if __name__ == "__main__": | |
| interface = gradio_interface() | |
| interface.queue() | |
| interface.launch() |