Update README.md

README.md

@@ -6,18 +6,23 @@ tags:
 - mergekit
 - lazymergekit
 - NousResearch/Hermes-2-Pro-Mistral-7B
-- NousResearch/Hermes-2-Pro-Mistral-7B
-- NousResearch/Hermes-2-Pro-Mistral-7B
-- NousResearch/Hermes-2-Pro-Mistral-7B
+- Mixtral
+- instruct
+- finetune
+- chatml
+- DPO
+- RLHF
+- gpt4
+- synthetic data
+- distillation
+- function calling
+- json mode
 ---
 
 # Hermes-2-Pro-Mixtral-4x7B
 
 Hermes-2-Pro-Mixtral-4x7B is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
-* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
-* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
-* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
+* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) X 4
 
 ## 🧩 Configuration
 
@@ -25,84 +30,177 @@ Hermes-2-Pro-Mixtral-4x7B is a Mixure of Experts (MoE) made with the following m
 experts:
   - source_model: NousResearch/Hermes-2-Pro-Mistral-7B
     positive_prompts:
-    - "reasoning"
-    - "logic"
-    - "problem-solving"
-    - "critical thinking"
-    - "analysis"
-    - "synthesis"
-    - "evaluation"
-    - "decision-making"
-    - "judgment"
-    - "insight"
-
+    - ""
   - source_model: NousResearch/Hermes-2-Pro-Mistral-7B
     positive_prompts:
-    - "program"
-    - "software"
-    - "develop"
-    - "build"
-    - "create"
-    - "design"
-    - "implement"
-    - "debug"
-    - "test"
-    - "code"
-    - "python"
-    - "programming"
-    - "algorithm"
-    - "function"
+    - ""
 
   - source_model: NousResearch/Hermes-2-Pro-Mistral-7B
     positive_prompts:
-    - "storytelling"
-    - "narrative"
-    - "fiction"
-    - "creative writing"
-    - "plot"
-    - "characters"
-    - "dialogue"
-    - "setting"
-    - "emotion"
-    - "imagination"
-    - "scene"
-    - "story"
-    - "character"
+    - ""
 
   - source_model: NousResearch/Hermes-2-Pro-Mistral-7B
     positive_prompts:
-    - "chat"
-    - "conversation"
-    - "dialogue"
-    - "discuss"
-    - "ask questions"
-    - "share thoughts"
-    - "explore ideas"
-    - "learn new things"
-    - "personal assistant"
-    - "friendly helper"
+    - ""
 ```
 
 ## 💻 Usage
 
+Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
+
+Note: To use function calling, you should see the github repo above.
+
 ```python
-!pip install -qU transformers bitsandbytes accelerate
+# Code to inference Hermes with HF Transformers
+# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
 
-from transformers import AutoTokenizer
-import transformers
 import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import LlamaTokenizer, MistralForCausalLM
+import bitsandbytes, flash_attn
 
-model = "Isotonic/Hermes-2-Pro-Mixtral-4x7B"
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Mistral-7B', trust_remote_code=True)
+model = MistralForCausalLM.from_pretrained(
+    "Isotonic/Hermes-2-Pro-Mixtral-4x7B",
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_8bit=False,
+    load_in_4bit=True,
+    use_flash_attention_2=True # ampere only
 )
 
-messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
-prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
+prompts = [
+    """<|im_start|>system
+You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
+<|im_start|>user
+Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
+<|im_start|>assistant""",
+    ]
+
+for chat in prompts:
+    print(chat)
+    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
+    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
+    print(f"Response: {response}")
+```
+### 📚 Function Calling:
+
+All code for utilizing, parsing, and building function calling templates are available on NousHermes's GitHub page:
+[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
+
+### 🖌️ Prompt Format
+
+Hermes 2 Pro 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 compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
+
+Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
+```
+<|im_start|>system
+You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
+<|im_start|>user
+Hello, who are you?<|im_end|>
+<|im_start|>assistant
+Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
+```
+
+This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
+`tokenizer.apply_chat_template()` method:
+
+```python
+messages = [
+    {"role": "system", "content": "You are Hermes 2."},
+    {"role": "user", "content": "Hello, who are you?"}
+]
+gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
+model.generate(**gen_input)
+```
+
+When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
+that the model continues with an assistant response.
+
+To utilize the prompt format without a system prompt, simply leave the line out.
+
+### 🖌️📚 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|>
+```
+
+### 🖌️📚 Prompt Format for JSON Mode / Structured Outputs
+
+Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
+
+Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
+
+```
+<|im_start|>system
+You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
+```
+
+Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
+
+# Citation:
+
+```bibtext
+@misc{Hermes-2-Pro-Mistral-7B, 
+      url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B]https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)}, 
+      title={Hermes-2-Pro-Mistral-7B}, 
+      author={"interstellarninja", "Teknium", "theemozilla", "karan4d", "huemin_art"}
+}
 ```