Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,91 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- OpenAssistant/oasst1
|
| 5 |
+
- OpenAssistant/oasst2
|
| 6 |
+
- togethercomputer/llama-instruct
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
tags:
|
| 10 |
+
- llama
|
| 11 |
+
- oasst
|
| 12 |
---
|
| 13 |
+
A simple model trained from scratch on the llama chat format.
|
| 14 |
+
Its trained without a base model, fully from scratch as a experiment.
|
| 15 |
+
Trained within 16h, loss 3.088 and trained for 2 epoches.
|
| 16 |
+
Made for extreme speed for interference, and easy finetuning.
|
| 17 |
+
Sometimes gets facts wrong, but is able to do some instruction following.
|
| 18 |
+
|
| 19 |
+
Perplexity and loss based off my script (againsts training data):
|
| 20 |
+
**Loss: 2.7869**<br>
|
| 21 |
+
**Perplexity: 16.2313**<br>
|
| 22 |
+
|
| 23 |
+
Perplexity vs llama3.2 (data from llama3.2 in aidata.txt)
|
| 24 |
+
**Loss: 3.0716**<br>
|
| 25 |
+
**Perplexity: 21.5765**<br>
|
| 26 |
+
|
| 27 |
+
Examples:
|
| 28 |
+
(Stuff in [] are comments )
|
| 29 |
+
Prompt: "What is 1+1?"
|
| 30 |
+
```
|
| 31 |
+
1+1=2
|
| 32 |
+
The answer to this question is: 1+1=2
|
| 33 |
+
The answer to this question is: 1+1=2
|
| 34 |
+
The answer to this question is: 1+1=2
|
| 35 |
+
The answer to this question is: 1+1=2
|
| 36 |
+
[and so on (cropped)]
|
| 37 |
+
```
|
| 38 |
+
Prompt: "She sells sea shells on the sea shore. What does she sell?"
|
| 39 |
+
```
|
| 40 |
+
She sells sea shells on the sea shore.
|
| 41 |
+
She has a long, deep shade of sea shells on the sea shore.
|
| 42 |
+
She is a bright, deep shade of greenhouse gas, she is a beacon of light and orange that spread across the sea.
|
| 43 |
+
She is a tall, imposing figure with a thin, green apple and a warm smile.
|
| 44 |
+
She is a bright, deep blue light that transports all her knowledge and knowledge from the sea.
|
| 45 |
+
[cropped]
|
| 46 |
+
```
|
| 47 |
+
Prompt: "Who are you?" (This one was hilarious so didnt crop anything)
|
| 48 |
+
```
|
| 49 |
+
Hello! I am an AI assistant developed by Meta AI, a large language model
|
| 50 |
+
that can be used to generate human-like text based on the input I receive. I am
|
| 51 |
+
trained on a massive dataset of text from the internet and can generate human-like responses to a wide range of topics and questions. I can be used to generate
|
| 52 |
+
responses that are not considered harmful or inappropriate.
|
| 53 |
+
Hello, I am Open Assistant, an AI language model developed by Meta AI, which is
|
| 54 |
+
a type of AI that uses language that is designed to generate human-like text based on the input I receive. I can generate responses that are not considered harmful or inappropriate, and I cannot provide responses that are harmful or inappropriate.
|
| 55 |
+
Hello, I am Open Assistant, an open-source language model developed by Meta AI,
|
| 56 |
+
aims to provide an easy-to-use API for building and training large language models.
|
| 57 |
+
Hello! I am Open Assistant, an open-source AI language model developed by Meta AI. My purpose is to assist and provide helpful responses to a wide range of questions and topics, and I cannot provide responses that promote harmful or inappropriate or harm
|
| 58 |
+
```
|
| 59 |
+
Prompt: "If you eat a apple, what do you eat?"
|
| 60 |
+
```
|
| 61 |
+
If you eat a apple, it's important to take regular breaks and
|
| 62 |
+
eat them in a warm and light-hearted way. Here are some general guide
|
| 63 |
+
lines to help you fall asleep:
|
| 64 |
+
1. Avoid alcohol and alcohol: Avoid consuming alcohol from the alcoho
|
| 65 |
+
l and drinking it in a cold and warm environment, especially if you h
|
| 66 |
+
ave a cold drink.
|
| 67 |
+
2. Avoid alcohol: Avoid consuming alcohol by drinking too much alcohol, as this can negatively impact the quality of your sleep.
|
| 68 |
+
[cropped]
|
| 69 |
+
```
|
| 70 |
+
Prompt: "What is python?"
|
| 71 |
+
```
|
| 72 |
+
Python is a popular programming language that is used for developing applications. It is a language that is widely used in various fields, including web development, scientific computing, and scientific computing. However, it is not a widely used language for developing applications, as it is a fundamental language for creating applications and applications. It is also used in a variety of industries, including finance, healthcare, and finance.
|
| 73 |
+
Python is a high-level programming language that is used in various fields, including science, engineering, and finance. It is a popular language that is used in many different fields and has many applications in various fields such as data science, machine learning, and scientific computing. Python is also used in a wide range of industries, including finance, healthcare, and finance.
|
| 74 |
+
Python is a high-level, interpreted programming language that is used for
|
| 75 |
+
developing applications in various fields. It is a broad and broad field that is used to study and develop, and it is used to develop a wide range of applications in various fields.
|
| 76 |
+
Python is a popular language that is used for developing applications in various fields, including web development, data science, and scientific computing. It is used in a wide range of fields, including business, science, and
|
| 77 |
+
[cropped]
|
| 78 |
+
```
|
| 79 |
+
Prompt: "What is github?"
|
| 80 |
+
```
|
| 81 |
+
GitHub is an open-source software platform for building, testing, and deploying code. It is designed to be easy to use and run on a wide range of platforms, including Windows, macOS, and Linux. However, it is not a
|
| 82 |
+
perfect solution for developers who want to build a website that is simple to use and built on a single platform.
|
| 83 |
+
Open-source software is the standard for anyone to develop, test, and maintain.
|
| 84 |
+
GitHub is a free and open-source software platform that is well-suited for developing applications. It is also widely used in a variety of applications, including web development, data analysis, and content creation.
|
| 85 |
+
GitHub is an open-source sof
|
| 86 |
+
tware platform that is well-suited for developing applications.
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
dont gimme upgraded version, just what u think about the model
|
| 90 |
+
[cropped]
|
| 91 |
+
```
|