---
base_model: Locutusque/Hyperion-3.0-Mistral-7B-DPO
datasets:
- Locutusque/hyperion-dpo-v1.0
language:
- en
library_name: transformers
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
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:\n\n1. Identify the given information:\n   - Initial velocity (v0):\
      \ 30 ft/sec\n   - Initial height (y0): 3 feet off the ground\n\n2. 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.\n\n3. Use Newton's second law\
      \ of motion to find the differential equation that describes the motion:\n \
      \  - 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.\n   - Since acceleration\
      \ equals force divided by mass, a = Fnet/m. In this case, m cancels out, so\
      \ a = g.\n   - The motion equation becomes: dv/dt = g = -32.2 ft/s^2 (since\
      \ we're moving upwards). This is the first differential equation.\n\n4. Since\
      \ we want to describe the ball's position (y) as well, we need another differential\
      \ equation. We can use kinematics equations:\n   - The velocity equation is\
      \ v = v0 + at. Substitute the value of a from step 3:\n     dv/dt = -32.2 ft/s^2.\
      \ Rewriting it as an integral:\n      ∫dv = -32.2 ft/s^2 * dt\n   - Integrating\
      \ with respect to time, we get v(t) = -16.1 t + C (constant of integration).\n\
      \n5. Now we have two equations, one for velocity and another for position:\n\
      \   - dv/dt = -32.2 ft/s^2 (equation 1)\n   - v(t) = -16.1 t + C (equation 2)\n\
      \n6. 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:\n\
      \   - Equation 2 becomes v0 = -16.1 * 0 + C, which simplifies to C = v0 = 30\
      \ ft/sec (initial velocity).\n\n7. Now we have both equations with the constants\
      \ filled in:\n   - dv/dt = -32.2 ft/s^2 (equation 1)\n   - v(t) = -16.1 t +\
      \ 30 ft/sec (equation 2)\n\n8. Finally, we need to find the ball's position\
      \ (y) as a function of time:\n   - Use the second kinematics equation y = y0\
      \ + v0*t + ½*a*t^2 (since acceleration is constant, it can be moved outside\
      \ the integral).\n   - Substitute the values for v0 and a:\n     y(t) = 3 ft\
      \ + (30 ft/sec) * t + (-½ * 32.2 ft/s^2) * t^2\n\nThat's it! The differential\
      \ equation describing the motion of the ball is:\n   - dv/dt = -32.2 ft/s^2\
      \ (equation 1)\n   - v(t) = -16.1 t + 30 ft/sec (equation 2)\n   - y(t) = 3\
      \ ft + (30 ft/sec) * t - (16.1 t^2) ft (equation 3)\n"
---

# ijohn07/Hyperion-3.0-Mistral-7B-DPO-Q8_0-GGUF
This model was converted to GGUF format from [`Locutusque/Hyperion-3.0-Mistral-7B-DPO`](https://huggingface.co/Locutusque/Hyperion-3.0-Mistral-7B-DPO) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Locutusque/Hyperion-3.0-Mistral-7B-DPO) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo ijohn07/Hyperion-3.0-Mistral-7B-DPO-Q8_0-GGUF --hf-file hyperion-3.0-mistral-7b-dpo-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo ijohn07/Hyperion-3.0-Mistral-7B-DPO-Q8_0-GGUF --hf-file hyperion-3.0-mistral-7b-dpo-q8_0.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo ijohn07/Hyperion-3.0-Mistral-7B-DPO-Q8_0-GGUF --hf-file hyperion-3.0-mistral-7b-dpo-q8_0.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo ijohn07/Hyperion-3.0-Mistral-7B-DPO-Q8_0-GGUF --hf-file hyperion-3.0-mistral-7b-dpo-q8_0.gguf -c 2048
```