Adding model card

README.md

@@ -1,3 +1,194 @@
 ---
+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
+```