Blink_Fast - Llama-3.1 70B

Model Description

Blink_Fast is an advanced fine-tuned version of the Llama-3.1 70B architecture, specifically tuned and prompted to excel as a highly capable AI coworker and general assistant.

For more details on the underlying capabilities, training foundation, and core architecture, see the Blink_Fast Technical Report (Blink was built upon the foundational Hermes 3 framework).

Blink_Fast is a collaborative language model designed with a strong focus on workplace productivity, professional reasoning, multi-turn workflow conversation, long-context coherence, and task automation.

The ethos of Blink_Fast is centered on creating a seamless digital teammate, providing powerful steerability, reliable task execution, and direct alignment with the user's professional needs.

This model delivers robust and reliable function calling, structured JSON output capabilities, general assistant versatility, and highly improved code generation skills.

Benchmarks

Blink_Fast is competitive, if not superior, to standard Llama-3.1 Instruct models at general and collaborative capabilities, with varying strengths and weaknesses attributable between the two.

Prompt Format

Blink_Fast uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.

System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.

This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.

This format enables OpenAI endpoint compatibility, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.

Prompt Format for Function Calling

Our model was trained on specific system prompts and structures for Function Calling.

You should use the system role with this message, followed by a function signature json as this example shows here.

<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n    Args:\\n        symbol (str): The stock symbol.\\n\\n    Returns:\\n        dict: A dictionary containing fundamental data.\\n            Keys:\\n                - \'symbol\': The stock symbol.\\n                - \'company_name\': The long name of the company.\\n                - \'sector\': The sector to which the company belongs.\\n                - \'industry\': The industry to which the company belongs.\\n                - \'market_cap\': The market capitalization of the company.\\n                - \'pe_ratio\': The forward price-to-earnings ratio.\\n                - \'pb_ratio\': The price-to-book ratio.\\n                - \'dividend_yield\': The dividend yield.\\n                - \'eps\': The trailing earnings per share.\\n                - \'beta\': The beta value of the stock.\\n                - \'52_week_high\': The 52-week high price of the stock.\\n                - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}}  </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>

To complete the function call, create a user prompt that follows the above system prompt, like so:

<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>

The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):

<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>

Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, tool like so:

<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>

The assistant will then read in that data from the function's response, and generate a natural language response:

<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37

This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>

Reality

In reality, Blink_Fast is just an exact duplicate of Hermes 3. It is our specialized prompting and user interface that make Blink unique, and these are not provided anywhere in this Hugging Face model.