Update README.md

README.md

@@ -1,199 +1,232 @@
 ---
-library_name: transformers
-tags: []
+language:
+- en
+license: llama3
+tags:
+- Llama-3
+- instruct
+- finetune
+- chatml
+- gpt4
+- synthetic data
+- distillation
+- function calling
+- json mode
+- axolotl
+- roleplaying
+- chat
+base_model: meta-llama/Meta-Llama-3.1-8B
+widget:
+- example_title: Hermes 3
+  messages:
+  - role: system
+    content: You are a sentient, superintelligent artificial general intelligence,
+      here to teach and assist me.
+  - role: user
+    content: What is the meaning of life?
+model-index:
+- name: Hermes-3-Llama-3.1-70B
+  results: []
 ---
 
-# Model Card for Model ID
+# Notice
+4bit bitsandbytes quant
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Hermes 3 - Llama-3.1 8B
 
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/bMcZ3sNNQK8SRZpHXBmwM.jpeg)
 
+## Model Description
 
-## Model Details
+Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research. 
 
-### Model Description
+For more details on new capabilities, training results, and more, see the [**Hermes 3 Technical Report**](https://nousresearch.com/wp-content/uploads/2024/08/Hermes-3-Technical-Report.pdf).
 
-<!-- Provide a longer summary of what this model is. -->
+Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+The ethos of the Hermes series of models is focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+The Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.
 
-### Model Sources [optional]
 
-<!-- Provide the basic links for the model. -->
+# Benchmarks
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+Hermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.
 
-## Uses
+Full benchmark comparisons below:
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/DIMca3M0U-ArWwtyIbF-k.png)
 
-### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+# Prompt Format
 
-[More Information Needed]
+Hermes 3 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
 
-### Downstream Use [optional]
+System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+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.
 
-[More Information Needed]
+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.
 
-### Out-of-Scope Use
+Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
+```
+<|im_start|>system
+You are Hermes 3, 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 3, 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 section addresses misuse, malicious use, and uses that the model will not work well for. -->
+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:
 
-[More Information Needed]
+```python
+messages = [
+    {"role": "system", "content": "You are Hermes 3."},
+    {"role": "user", "content": "Hello, who are you?"}
+]
+gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
+model.generate(**gen_input)
+```
 
-## Bias, Risks, and Limitations
+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.
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+To utilize the prompt format without a system prompt, simply leave the line out.
 
-[More Information Needed]
 
-### Recommendations
+## Prompt Format for Function Calling
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+Our model was trained on specific system prompts and structures for Function Calling. 
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+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|>
+```
 
-## How to Get Started with the Model
+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|>
+```
 
-Use the code below to get started with the model.
+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|>
+```
 
-[More Information Needed]
+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|>
+```
 
-## Training Details
+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
 
-### Training Data
+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|>
+```
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-[More Information Needed]
+## Prompt Format for JSON Mode / Structured Outputs
 
-### Training Procedure
+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.
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+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.
+
+
+# Inference
+
+Here is example code using HuggingFace Transformers to inference the model
+
+```python
+# Code to inference Hermes with HF Transformers
+# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
+import bitsandbytes, flash_attn
+
+tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-3-Llama-3.1-8B', trust_remote_code=True)
+model = LlamaForCausalLM.from_pretrained(
+    "NousResearch/Hermes-3-Llama-3.1-8B",
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_8bit=False,
+    load_in_4bit=True,
+    use_flash_attention_2=True
+)
 
-#### Preprocessing [optional]
+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}")
+```
+
+You can also run this model with vLLM, by running the following in your terminal after `pip install vllm`
+
+`vllm serve NousResearch/Hermes-3-Llama-3.1-8B`
+
+## Inference Code for Function Calling:
+
+All code for utilizing, parsing, and building function calling templates is available on our github:
+[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/oi4CiGh50xmoviUQnh8R3.png)
+
+
+## Quantized Versions:
+
+GGUF Quants: https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF
 
-[More Information Needed]
+# How to cite:
 
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+```bibtext
+@misc{Hermes-3-Llama-3.1-8B, 
+      url={[https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B]https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B)}, 
+      title={Hermes-3-Llama-3.1-8B}, 
+      author={"Teknium", "theemozilla", "Chen Guang", "interstellarninja",  "karan4d", "huemin_art"}
+}
+```