DeepHermes-3-Mistral-24B-Preview

You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import flash_attn
import time

tokenizer = AutoTokenizer.from_pretrained("NousResearch/DeepHermes-3-Mistral-24B-Preview")

model = AutoModelForCausalLM.from_pretrained(
    "NousResearch/DeepHermes-3-Mistral-24B-Preview",
    torch_dtype=torch.float16,
    device_map="auto",
    attn_implementation="flash_attention_2",
)

messages = [
    {
        "role": "system",
        "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem."
    },
    {
        "role": "user",
        "content": "What is y if y=2*2-4+(3*2)"
    }
]

input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=2500, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
print(f"Generated Tokens: {generated_ids.shape[-1:]}")
response = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import flash_attn
import time

tokenizer = AutoTokenizer.from_pretrained("NousResearch/DeepHermes-3-Mistral-24B-Preview")

model = AutoModelForCausalLM.from_pretrained(
    "NousResearch/DeepHermes-3-Mistral-24B-Preview",
    torch_dtype=torch.float16,
    device_map="auto",
    attn_implementation="flash_attention_2",
)

messages = [
    {
        "role": "system",
        "content": "You are Hermes, an AI assistant"
    },
    {
        "role": "user",
        "content": "What are the most interesting things to do in Paris?"
    }
]

input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=2500, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
print(f"Generated Tokens: {generated_ids.shape[-1:]}")
response = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")

<|start_header_id|>system<|end_header_id|>
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><|eot_id|><|start_header_id|>user<|end_header_id|>

Fetch the stock fundamentals data for Tesla (TSLA)<|eot_id|><|start_header_id|>assistant<|end_header_id|>

<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|eot_id|><|start_header_id|>tool<|end_header_id|>

<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>
<|eot_id|><|start_header_id|>assistant<|end_header_id|>

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.<|eot_id|><|start_header_id|>user<|end_header_id|>

<|start_header_id|>system<|end_header_id|>
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|eot_id|>

@misc{
      title={DeepHermes 3 Preview}, 
      author={Teknium and Roger Jin and Chen Guang and Jai Suphavadeeprasit and Jeffrey Quesnelle},
      year={2025}
}