README.md

metadata

library_name: peft
base_model: meta-llama/Meta-Llama-3-8B
language:
  - en
pipeline_tag: text-generation
widget:
  - text: How many helicopters can a human eat in one sitting?
tags:
  - Δ
  - LoRA

Model Details

$${\text{🗽}}_{\mathrm{\Delta }LoRA}={\mathrm{\Delta }}_{({\text{🦙}}_W,{\text{🗽}}_W)}🗽\_\{\Delta LoRA\}\; =\; \backslash Delta\_\{(🦙\_W,\; 🗽\_W)\}$$

$${\text{🦙}}_W+{\text{🗽}}_{\mathrm{\Delta }LoRA}={\text{🗽}}_W{\text{🦙}}_W-{\text{🗽}}_{\mathrm{\Delta }LoRA}={\text{🦙}}_W🦙\_W\; +\; 🗽\_\{\Delta LoRA\}\; =\; 🗽\_W\; \backslash \backslash \; 🦙\_W\; -\; 🗽\_\{\Delta LoRA\}\; =\; 🦙\_W$$

How to Get Started with the Model

Find the original here https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B

Use the code below to get started with the model.

# pip install transformers peft

import torch
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer

model_id = "meta-llama/Meta-Llama-3-8B"
peft_model_id = "typeof/Hermes-2-Pro-Llama-3-8B-delta-lora"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

system_prompt = """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>"""

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Fetch the stock fundamentals data for Tesla (TSLA)"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

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

... call tool and pass back prompt 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|>

<|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|>

Summary

LoRA QLoRA