nateraw/mistral-7b-openorca 🔢📝 → 📝

▶️ 65.9K runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub

chat code-generation question-answering text-generation text-translation

About

Mistral-7B-v0.1 fine tuned for chat with the OpenOrca dataset.

Example Output

Prompt:

"Explain what's so cool about Python"

Output

To explain what's so cool about Python, let's break it down into several key aspects:

Versatility: Python is a versatile programming language that can be used for a wide range of tasks, including web development, data analysis, machine learning, and more. This makes it a popular choice for developers and data scientists alike.
Ease of use: Python has a simple and easy-to-read syntax, which makes it beginner-friendly. This means that even if you're new to programming, you can quickly pick up the language and start writing code.
Open-source libraries: Python has a vast ecosystem of open-source libraries and frameworks, such as NumPy, Pandas, and TensorFlow, which can be used to accelerate development and make complex tasks easier.
Community support: The Python community is large and active, which means there's plenty of help available if you run into any issues or have questions. Additionally, the community contributes to the development and improvement of the language.
Portability: Python code can be run on various platforms, including Windows, macOS, and Linux, making it a great choice for cross-platform development.
Scalability: Python's code can be easily scaled up or down depending on the requirements of the project, making it suitable for both small and large-scale applications.
Interpreted language: Python is an interpreted language, which means that the code is executed directly by the Python interpreter, without the need for compiling. This can save time during development and deployment.

In summary, Python is a cool programming language because it is versatile, easy to learn, has a large community and library support, is portable, and is scalable. These factors make it a popular choice for a wide range of applications and developers.

Performance Metrics

4.97s Prediction Time

4.99s Total Time

All Input Parameters

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Explain what's so cool about Python",
  "temperature": 0.2,
  "max_new_tokens": 512,
  "prompt_template": "<|im_start|>system\nYou are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!\n<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
  "presence_penalty": 0,
  "frequency_penalty": 0
}

Input Parameters

top_k Type: integerDefault: 50: The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
top_p Type: numberDefault: 0.95: A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string
temperature Type: numberDefault: 0.8: The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 512: The maximum number of tokens the model should generate as output.
prompt_template Type: stringDefault: <|im_start|>system You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers! <|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant: The template used to format the prompt. The input prompt is inserted into the template using the `{prompt}` placeholder.
presence_penalty Type: numberDefault: 0: Presence penalty
frequency_penalty Type: numberDefault: 0: Frequency penalty

Output Schema

Output

Type: array • Items Type: string

Example Execution Logs

Generated 398 tokens in 4.958377122879028 seconds.

Version Details

Version ID: 7afe21847d582f7811327c903433e29334c31fe861a7cf23c62882b181bacb88
Version Created: October 14, 2023

Run on Replicate →