Spaces:
Runtime error
Runtime error
| import spaces | |
| import gradio as gr | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer | |
| from threading import Thread | |
| # Lazy loading the model to meet huggingface stateless GPU requirements | |
| # Defining a custom stopping criteria class for the model's text generation. | |
| class StopOnTokens(StoppingCriteria): | |
| def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool: | |
| stop_ids = [50256, 50295] # IDs of tokens where the generation should stop. | |
| for stop_id in stop_ids: | |
| if input_ids[0][-1] == stop_id: # Checking if the last generated token is a stop token. | |
| return True | |
| return False | |
| # Function to generate model predictions. | |
| def predict(message, history): | |
| torch.set_default_device("cuda") | |
| # Loading the tokenizer and model from Hugging Face's model hub. | |
| tokenizer = AutoTokenizer.from_pretrained( | |
| "macadeliccc/SOLAR-math-2x10.7b", | |
| trust_remote_code=True | |
| ) | |
| model = AutoModelForCausalLM.from_pretrained( | |
| "macadeliccc/SOLAR-math-2x10.7b", | |
| torch_dtype="auto", | |
| load_in_4bit=True, | |
| trust_remote_code=True | |
| ) | |
| history_transformer_format = history + [[message, ""]] | |
| stop = StopOnTokens() | |
| # Formatting the input for the model. | |
| system_prompt = "<|im_start|>system\nYou are Solar, a helpful AI assistant.<|im_end|>" | |
| messages = system_prompt + "".join(["".join(["\n<|im_start|>user\n" + item[0], "<|im_end|>\n<|im_start|>assistant\n" + item[1]]) for item in history_transformer_format]) | |
| input_ids = tokenizer([messages], return_tensors="pt").to('cuda') | |
| streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True) | |
| generate_kwargs = dict( | |
| input_ids, | |
| streamer=streamer, | |
| max_new_tokens=256, | |
| do_sample=True, | |
| top_p=0.95, | |
| top_k=50, | |
| temperature=0.7, | |
| num_beams=1, | |
| stopping_criteria=StoppingCriteriaList([stop]) | |
| ) | |
| t = Thread(target=model.generate, kwargs=generate_kwargs) | |
| t.start() # Starting the generation in a separate thread. | |
| partial_message = "" | |
| for new_token in streamer: | |
| partial_message += new_token | |
| if '<|im_end|>' in partial_message: # Breaking the loop if the stop token is generated. | |
| break | |
| yield partial_message | |
| # Setting up the Gradio chat interface. | |
| gr.ChatInterface(predict, | |
| description=""" | |
| <center><img src="https://huggingface.co/macadeliccc/SOLAR-math-2x10.7b-v0.2/resolve/main/solar.png" width="33%"></center>\n\n | |
| Chat with [macadeliccc/SOLAR-math-2x10.7b-v0.2](https://huggingface.co/macadeliccc/SOLAR-math-2x10.7b-v0.2), the first Mixture of Experts made by merging two fine-tuned [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) models. | |
| This model (19.2B param) scores top 5 on several evaluations. Output is considered experimental.\n\n | |
| ❤️ If you like this work, please follow me on [Hugging Face](https://huggingface.co/macadeliccc) and [LinkedIn](https://www.linkedin.com/in/tim-dolan-python-dev/). | |
| """, | |
| examples=[ | |
| 'Can you solve the equation 2x + 3 = 11 for x?', | |
| 'How does Fermats last theorem impact number theory?', | |
| 'What is a vector in the scope of computer science rather than physics?', | |
| 'Use a list comprehension to create a list of squares for numbers from 1 to 10.', | |
| 'Recommend some popular science fiction books.', | |
| 'Can you write a short story about a time-traveling detective?' | |
| ], | |
| theme=gr.themes.Soft(primary_hue="purple"), | |
| ).launch() |