Bagel 8b V1.0

🚀 A bagel, with everything (except DPO)

This model, named "llama-3-bagel-8b-v1.0", is built upon Meta's llama-3. It's a fine - tuned version of llama - 3 - 8b using the bagel dataset, standardized on the llama - 3 instruct prompt format instead of 4 different prompt formats.

🚀 Quick Start

The model is ready for use once you've set up the appropriate environment. You can refer to the bagel repository for more details on the datasets used. The DPO version will be available soon here.

✨ Features

• Fine - tuned on Diverse Datasets: Utilizes a wide range of data sources, including AI - related datasets, coding problems, and multi - lingual content, to enhance its performance in various tasks.
• Standardized Prompt Format: Adopts the llama - 3 instruct prompt format, making it easier to use and integrate.
• Multiple Prompting Strategies: Supports different prompting strategies such as context - obedient question answering, summarization, function calling, chain of thought, and reWOO style function planning/execution.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

Here is an example of using the tokenizer's apply_chat_template method to format prompts:

import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("jondurbin/bagel-8b-v1.0", trust_remote_code=True)
chat = [
  {"role": "system", "content": "You are Bob, a friendly AI assistant."},
  {"role": "user", "content": "Hello, how are you?"},
  {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
  {"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))

Advanced Usage

Context Obedient Question Answering

The following is an example of a closed - context prompt for question answering:

BEGININPUT
BEGINCONTEXT
[date: 2021-01-01]
[url: https://web.site/123]
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are blueberries?  Source?
ENDINSTRUCTION

The model's response should be:

Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123

Summarization

For summarization tasks, use the following format:

BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION

Function Calling

There are two main function - calling formats:

Format 1: From airoboros dataset Prompt:

As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.

Input: I want to know how many times 'Python' is mentioned in my text file.

Available functions:
file_analytics:
  description: This tool performs various operations on a text file.
  params:
    action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
    filters:
      keyword: The word or phrase we want to search for.

Response:

{
  "function": "file_analytics",
  "params": {
    "action": "count_occurrences",
    "filters": {
      "keyword": "Python"
    }
  }
}

Format 2: GlaiveAI function calling Prompt:

<|start_header_id|>system<|end_header_id|>
You are a helpful assistant with access to the following functions. Use them if required -
{
    "name": "generate_random_name",
    "description": "Generate a random name",
    "parameters": {
        "type": "object",
        "properties": {
            "gender": {
                "type": "string",
                "description": "The gender of the name (e.g. male, female)"
            }
        },
        "required": [
            "gender"
        ]
    }
}
<|eot_id|>
<|start_header_id|>user<|end_header_id|>
I need a random male name for my novel's character.<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>

Response:

<|begin_func|> {"name": "generate_random_name", "arguments": '{"gender": "male"}'} <|end_func|>

Then, re - prompt the model with the function response:

<|begin_func_response|>{"name": "James"}<|end_func_response|>

The final response:

How about the name "James" for your novel's character?

Chain of Thought

Example prompt:

A group of people decide to play a round - robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.

Example response:

Solution 1:
In a round - robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players). 

The formula for combinations is nC2 = n(n - 1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:

n(n - 1)/2 = 45

Solving this equation gives us n = 10.

Final answer: There were 10 players in the tournament.

Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers. 

If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9 = 45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.

Final answer: There were 10 players in the tournament.

Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round - robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.

Final answer: There were 10 players in the tournament.

Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round - robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.

Best and final answer: There were 10 players in the tournament.

📚 Documentation

Data Sources

There are numerous data sources used in the bagel models. See https://github.com/jondurbin/bagel for more information.

Only train splits are used, and a decontamination by cosine similarity is performed at the end as a sanity check against common benchmarks. If you don't know the difference between train and test, please learn.

Prompt Formatting

The model uses the llama - 3 - instruct prompt template, and it's provided in the tokenizer config. You can use the apply_chat_template method to accurately format prompts.

Prompting Strategies

Context Obedient Question Answering

This is a special prompt format for answering questions from provided context, e.g., RAG. The model was trained to ignore its prior knowledge and use the context to answer questions, and was tuned to limit responses to the provided context to reduce hallucinations.

The format for a closed - context prompt is as follows:

BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s).  The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION

It's advisable to add "Don't make up answers if you don't know." to the instruction block.

Summarization

The summarization prompt format is the same as context - obedient question answering, and it's fine - tuned with this dataset.

Function Calling

There are two primary function - calling formats: one from the airoboros dataset and the GlaiveAI function - calling format.

Chain of Thought

This strategy is useful for having the model propose multiple possible responses, reason through each, and select the most probable answer.

reWOO style function planning/execution

The model supports execution planning for complex instructions.

🔧 Technical Details

The model is a fine - tuned version of the Meta - llama/Meta - Llama - 3 - 8B base model. It uses a wide range of datasets for training to enhance its performance in different tasks.

📄 License

This project is licensed under the llama3 license.