--- base_model: Locutusque/Hyperion-3.0-Mistral-7B-DPO library_name: transformers license: apache-2.0 language: - en widget: - example_title: Reasoning text: > <|im_start|>system You are Hyperion, an AI assistant developed by Sebastian Gabarain with a focus in reasoning, coding, science, and other general-purpose subjects. You are an AI assistant that follows instruction extremely well. Help as much as you can. <|im_end|> <|im_start|>user In this task, you are given a description of an object and its surroundings. Your task is to describe the motion of the object mentioned in the description using differential equations. The answer should be a mathematical expression in t. Description: A ball is thrown up at 30 ft/sec from 3 feet off the ground. Solve this step-by-step, explaining each step in detail. <|im_end|> <|im_start|>assistant output: text: > Hyperion here. The task requires you to describe the motion of a ball thrown up using differential equations. Here's the detailed explanation of how to solve it: 1. Identify the given information: - Initial velocity (v0): 30 ft/sec - Initial height (y0): 3 feet off the ground 2. Determine the acceleration due to gravity (g) at sea level, which is approximately -32.2 ft/s^2. Since we're dealing with a short distance and not very high altitudes, we can consider this value of g as constant. 3. Use Newton's second law of motion to find the differential equation that describes the motion: - The net force acting on the ball is the sum of gravity (mg) and air resistance (which we will neglect for simplicity). So, Fnet = mg. - Since acceleration equals force divided by mass, a = Fnet/m. In this case, m cancels out, so a = g. - The motion equation becomes: dv/dt = g = -32.2 ft/s^2 (since we're moving upwards). This is the first differential equation. 4. Since we want to describe the ball's position (y) as well, we need another differential equation. We can use kinematics equations: - The velocity equation is v = v0 + at. Substitute the value of a from step 3: dv/dt = -32.2 ft/s^2. Rewriting it as an integral: ∫dv = -32.2 ft/s^2 * dt - Integrating with respect to time, we get v(t) = -16.1 t + C (constant of integration). 5. Now we have two equations, one for velocity and another for position: - dv/dt = -32.2 ft/s^2 (equation 1) - v(t) = -16.1 t + C (equation 2) 6. We need to find the constant C using the initial conditions given in the problem. We know that initially, at time t=0, the ball's velocity is v0: - Equation 2 becomes v0 = -16.1 * 0 + C, which simplifies to C = v0 = 30 ft/sec (initial velocity). 7. Now we have both equations with the constants filled in: - dv/dt = -32.2 ft/s^2 (equation 1) - v(t) = -16.1 t + 30 ft/sec (equation 2) 8. Finally, we need to find the ball's position (y) as a function of time: - Use the second kinematics equation y = y0 + v0*t + ½*a*t^2 (since acceleration is constant, it can be moved outside the integral). - Substitute the values for v0 and a: y(t) = 3 ft + (30 ft/sec) * t + (-½ * 32.2 ft/s^2) * t^2 That's it! The differential equation describing the motion of the ball is: - dv/dt = -32.2 ft/s^2 (equation 1) - v(t) = -16.1 t + 30 ft/sec (equation 2) - y(t) = 3 ft + (30 ft/sec) * t - (16.1 t^2) ft (equation 3) datasets: - Locutusque/hyperion-dpo-v1.0 model_creator: Locutusque model_name: Hyperion-3.0-Mistral-7B-DPO model_type: mistral pipeline_tag: text-generation inference: false tags: - quantized - 4-bit - AWQ - text-generation - autotrain_compatible - endpoints_compatible - chatml quantized_by: Suparious --- # Locutusque/Hyperion-3.0-Mistral-7B-DPO AWQ - Model creator: [Locutusque](https://huggingface.co/Locutusque) - Original model: [Hyperion-3.0-Mistral-7B-DPO](https://huggingface.co/Locutusque/Hyperion-3.0-Mistral-7B-DPO) ## Model Summary - **Model Name**: Locutusque/Hyperion-3.0-Mistral-7B-DPO - **Base Model**: mistralai/Mistral-7B-v0.1 - **Publisher**: Locutusque - **Model Type**: Question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, logical reasoning - **Language**: Multi-domain, English language - **License**: Apache-2.0 `Locutusque/Hyperion-3.0-Mistral-7B-DPO` is an advanced language model fine-tuned with a dataset of 20,000 meticulously curated high-quality preference pairs using Direct Preference Optimization (DPO). The examples were generated by GPT-4 to ensure exceptional quality and relevance. This model is designed to provide superior performance across a wide range of complex tasks, including question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, and logical reasoning. ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/Hyperion-3.0-Mistral-7B-DPO-AWQ" system_message = "You are Hyperion, incarnated as a powerful AI." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code ## Prompt template: ChatML ```plaintext <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ```