--- language: - en pipeline_tag: text-generation inference: false tags: - pytorch - mistralai - mistral - mistral-7b - functions - function calling extra_gated_prompt: "Access to this model requires the purchase of a license [here](https://buy.stripe.com/cN2cNybSdgyncV25kQ)" extra_gated_fields: Name: text Affiliation: text Email: text I agree to the terms of the license described on the model card: checkbox I have purchased a license: checkbox --- # Function Calling Mistral 7B - Function calling Mistral extends the HuggingFace Mistral 7B Instruct model with function calling capabilities. - The model responds with a structured json argument with the function name and arguments. **Recent Updates** - October 11th 2023 -> added Mistral 7B with function calling - October 11th 2023 -> new models pushed, trained on an improved underlying dataset **Improvements with v2** 1. Shortened syntax: Only function descriptions are needed for inference and no added instruction is required. 2. Function descriptions are moved outside of the system prompt. This avoids the behaviour of function calling being affected by how the system prompt had been trained to influence the model. Available models: - Llama-7B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-adapters-v2)), ([GGUF - files are in the main branch]) - Free - Mistral-7B-Instruct-v0.1 with function calling ([Base Model](https://huggingface.co/Trelis/Mistral-7B-Instruct-v0.1-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Mistral-7B-Instruct-v0.1-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/cN2cNybSdgyncV25kQ) - Llama-13B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/9AQ7te3lHdmbdZ68wz) - CodeLlama-34B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/cN27teg8t2Hx5sA8wM) - Llama-70B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/8wMdRC1dzci75sA4gy) ## Performance and Tips 1. Larger models are better at handling function calling. The cross entropy training losses are approximately 0.5 for 7B, 0.4 for 13B, 0.3 for 70B. The absolute numbers don't mean anything but the relative values offer a sense of relative performance. 1. Provide very clear function descriptions, including whether the arguments are required or what the default values should be. 1. Make sure to post-process the language model's response to check that all necessary information is provided by the user. If not, prompt the user to let them know they need to provide more info (e.g. their name, order number etc.) Check out this video overview of performance [here](https://www.loom.com/share/8d7467de95e04af29ff428c46286946c?sid=683c970e-6063-4f1e-b184-894cc1d96115) ## Licensing Llama-7B with function calling is licensed according to the Meta Community license. Mistral-7B, Llama-13B, Code-llama-34b, Llama-70B and Falcon-180B with function calling require the purchase of access. - Commercial license purchase required per user. - Licenses are not transferable to other users/entities. Use of all Llama models with function calling is further subject to terms in the [Meta license](https://ai.meta.com/resources/models-and-libraries/llama-downloads/). ## Dataset The dataset used for training this model can be found at [Trelis Function Calling Extended Dataset](https://huggingface.co/datasets/Trelis/function_calling_extended). ## Inference **Quick Start in Google Colab** Try out this notebook [fLlama_Inference notebook](https://colab.research.google.com/drive/1Ow5cQ0JNv-vXsT-apCceH6Na3b4L7JyW?usp=sharing) **Commercial Applications** You can this model with [text-generation-interface](https://github.com/huggingface/text-generation-inference) and [chat-ui](https://github.com/huggingface/chat-ui) Here is the [github for setup](https://github.com/TrelisResearch/tgi-chat-ui-function-calling) And here is a video showing it working with [llama-2-7b-chat-hf-function-calling-v2](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2) (note that we've now moved to v2) Note that you'll still need to code the server-side handling of making the function calls (which obviously depends on what functions you want to use). **Run on your laptop** Run on your laptop [video and juypter notebook](https://youtu.be/nDJMHFsBU7M) ## Syntax ### Prompt Templates The function descriptions must be wrapped within a function block. You can put this function below before or after the system message block. Example without a system message: ``` # Define the roles and markers B_INST, E_INST = "[INST]", "[/INST]" B_FUNC, E_FUNC = "", "\n\n" functionList = {function_1_metadata}{function_2_metadata}... user_prompt = '...' # Format your prompt template prompt = f"{B_FUNC}{functionList.strip()}{E_FUNC}{B_INST} {user_prompt.strip()} {E_INST}\n\n" ``` Example with a system message: ``` # Define the roles and markers B_INST, E_INST = "[INST]", "[/INST]" B_FUNC, E_FUNC = "", "\n\n" B_SYS, E_SYS = "<>\n", "\n<>\n\n" # assuming functionList is defined as above system_prompt = '...' user_prompt = '...' # Format your prompt template prompt = f"{B_FUNC}{functionList.strip()}{E_FUNC}{B_INST} {B_SYS}{system_prompt.strip()}{E_SYS}{user_prompt.strip()} {E_INST}\n\n" ``` Notice that the function block is placed at the very start of the sequence, before 'B_INST'. ### Function Metadata Template functionMetadata should be a string representation of a JSON object, like this: ``` "functionMetadata": { "function": "search_bing", "description": "Search the web for content on Bing. This allows users to search online/the internet/the web for content.", "arguments": [ { "name": "query", "type": "string", "description": "The search query string" } ] } ''' ``` and the language model should respond with a json object formatted like this: ``` { "function": "function_name", "arguments": { "argument1": "argument_value", "argument2": "argument_value" } } ``` It is recommended to handle cases where: - There is no json object in the response - The response contains text in addition to the json response ### Sample functionList ``` { "function": "search_bing", "description": "Search the web for content on Bing. This allows users to search online/the internet/the web for content.", "arguments": [ { "name": "query", "type": "string", "description": "The search query string" } ] } { "function": "search_arxiv", "description": "Search for research papers on ArXiv. Make use of AND, OR and NOT operators as appropriate to join terms within the query.", "arguments": [ { "name": "query", "type": "string", "description": "The search query string" } ] } ``` ### Training Set Argument Types Models were fine-tuned on argument types including strings, numbers and arrays. The training set includes function calls with 0, 1, 2 or 3 arguments. The larger the model the better it will generalise beyond these types. Here is a function call with an array: ``` { "function": "delete_file", "arguments": { "fileNames": [ "Dissecting Transformer Length Extrapolation via The Lens of Receptive Field Analysis", "Luna- Linear Unified Nested Attention", "Substack_Inc_2021_2020_GAAP_Audited_Financials" ] } } ``` Here is a function call with three arguments: ``` { "function": "save_chat", "arguments": { "fileName": "KiteDiscussion", "fileDescription": "Notes on one and two stringed kites", "fileContent": "--- **Types of Kite** There are one and two string kites. The two string ones are easier to control, although you can get the cords tangled. The one-stringed ones are sometimes used for kite fights, and you lose the kite and have to run after it if the string breaks. ---" } } ``` ~ Below follows information on the original Llama 2 model... ~ # Model Card for Mistral-7B-Instruct-v0.1 The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets. For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/). ## Instruction format In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id. E.g. ``` text = "[INST] What is your favourite condiment? [/INST]" "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen! " "[INST] Do you have mayonnaise recipes? [/INST]" ``` This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method: ```python from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1") tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") model_inputs = encodeds.to(device) model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) decoded = tokenizer.batch_decode(generated_ids) print(decoded[0]) ``` ## Model Architecture This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer ## Troubleshooting - If you see the following error: ``` Traceback (most recent call last): File "", line 1, in File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained config, kwargs = AutoConfig.from_pretrained( File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained config_class = CONFIG_MAPPING[config_dict["model_type"]] File "/transformers/models/auto/configuration_auto.py", line 723, in getitem raise KeyError(key) KeyError: 'mistral' ``` Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers This should not be required after transformers-v4.33.4. ## Limitations The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.