--- base_model: gorilla-llm/gorilla-openfunctions-v2 language: - en pipeline_tag: text-generation license: apache-2.0 model_creator: Gorilla LLM (UC Berkely) model_name: Gorilla OpenFunctions v2 model_type: deepseek quantized_by: CISC --- # Gorilla OpenFunctions v2 - SOTA GGUF - Model creator: [Gorilla LLM](https://huggingface.co/gorilla-llm) - Original model: [Gorilla OpenFunctions v2](https://huggingface.co/gorilla-llm/gorilla-openfunctions-v2) ## Description This repo contains State Of The Art quantized GGUF format model files for [Gorilla OpenFunctions v2](https://huggingface.co/gorilla-llm/gorilla-openfunctions-v2). Quantization was done with an importance matrix that was trained for ~1M tokens (256 batches of 4096 tokens) of training data from [gorilla_openfunctions_v1_train.json](https://github.com/ShishirPatil/gorilla/raw/main/openfunctions/openfunctions-v1/gorilla_openfunctions_v1_train.json). Everything has been reconverted and quantized with a new importance matrix using llama.cpp from April 29th 2024 onwards, as of commit [f4ab2a4](https://github.com/ggerganov/llama.cpp/commit/f4ab2a41476600a98067a9474ea8f9e6db41bcfa) to ensure correct pre-tokenization. The new GGUFs will work with older llama.cpp, but this may not generate correct prompt tokens, please use a recent build to ensure the best possible results! ## Prompt template: Gorilla OpenFunctions v2 ``` You are an AI programming assistant, utilizing the Gorilla LLM model, developed by Gorilla LLM, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer. ### Instruction: <>[{"name": "function_name", "description": "Description", "parameters": {...}}, ...] <>{prompt} ### Response: ``` ## Compatibility These quantised GGUFv3 files are compatible with llama.cpp from February 27th 2024 onwards, as of commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307) They are also compatible with many third party UIs and libraries provided they are built using a recent llama.cpp. ## Explanation of quantisation methods
Click to see details The new methods available are: * GGML_TYPE_IQ1_S - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.56 bits per weight (bpw) * GGML_TYPE_IQ1_M - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.75 bpw * GGML_TYPE_IQ2_XXS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.06 bpw * GGML_TYPE_IQ2_XS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.31 bpw * GGML_TYPE_IQ2_S - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.5 bpw * GGML_TYPE_IQ2_M - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.7 bpw * GGML_TYPE_IQ3_XXS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.06 bpw * GGML_TYPE_IQ3_XS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.3 bpw * GGML_TYPE_IQ3_S - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.44 bpw * GGML_TYPE_IQ3_M - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.66 bpw * GGML_TYPE_IQ4_XS - 4-bit quantization in super-blocks with an importance matrix applied, effectively using 4.25 bpw * GGML_TYPE_IQ4_NL - 4-bit non-linearly mapped quantization with an importance matrix applied, effectively using 4.5 bpw Refer to the Provided Files table below to see what files use which methods, and how.
## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [gorilla-openfunctions-v2.IQ1_S.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ1_S.gguf) | IQ1_S | 1 | 1.5 GB| 3.5 GB | smallest, significant quality loss - **TBD**: Waiting for [this issue](https://github.com/ggerganov/llama.cpp/issues/5996) to be resolved | | [gorilla-openfunctions-v2.IQ2_XXS.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ2_XXS.gguf) | IQ2_XXS | 2 | 1.8 GB| 3.8 GB | very small, high quality loss | | [gorilla-openfunctions-v2.IQ2_XS.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ2_XS.gguf) | IQ2_XS | 2 | 1.9 GB| 3.9 GB | very small, high quality loss | | [gorilla-openfunctions-v2.IQ2_S.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ2_S.gguf) | IQ2_S | 2 | 2.1 GB| 4.1 GB | small, substantial quality loss | | [gorilla-openfunctions-v2.IQ2_M.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ2_M.gguf) | IQ2_M | 2 | 2.2 GB| 4.2 GB | small, greater quality loss | | [gorilla-openfunctions-v2.IQ3_XXS.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ3_XXS.gguf) | IQ3_XXS | 3 | 2.5 GB| 4.5 GB | very small, high quality loss | | [gorilla-openfunctions-v2.IQ3_XS.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ3_XS.gguf) | IQ3_XS | 3 | 2.7 GB| 4.7 GB | small, substantial quality loss | | [gorilla-openfunctions-v2.IQ3_S.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ3_S.gguf) | IQ3_S | 3 | 2.8 GB| 4.8 GB | small, greater quality loss | | [gorilla-openfunctions-v2.IQ3_M.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ3_M.gguf) | IQ3_M | 3 | 3.0 GB| 5.0 GB | medium, balanced quality - recommended | | [gorilla-openfunctions-v2.IQ4_XS.gguf](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.IQ4_XS.gguf) | IQ4_XS | 4 | 3.4 GB| 5.4 GB | small, substantial quality loss | Generated importance matrix file: [gorilla-openfunctions-v2.imatrix.dat](https://huggingface.co/CISCai/gorilla-openfunctions-v2-SOTA-GGUF/blob/main/gorilla-openfunctions-v2.imatrix.dat) **Note**: the above RAM figures assume no GPU offloading with 4K context. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307) or later. ```shell ./main -ngl 33 -m gorilla-openfunctions-v2.IQ3_M.gguf --color -c 16384 --temp 0 --repeat-penalty 1.1 -p "You are an AI programming assistant, utilizing the Gorilla LLM model, developed by Gorilla LLM, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\n### Instruction: <>{functions}\n<>{prompt}\n### Response: " ``` Change `-ngl 33` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 16384` to the desired sequence length. If you want to have a chat-style conversation, replace the `-p ` argument with `-i -ins` If you are low on V/RAM try quantizing the K-cache with `-ctk q8_0` or even `-ctk q4_0` for big memory savings (depending on context size). There is a similar option for V-cache (`-ctv`), however that is [not working yet](https://github.com/ggerganov/llama.cpp/issues/4425). For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) module. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://llama-cpp-python.readthedocs.io/en/latest/). #### First install the package Run one of the following commands, according to your system: ```shell # Prebuilt wheel with basic CPU support pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu # Prebuilt wheel with NVidia CUDA acceleration pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 (or cu122 etc.) # Prebuilt wheel with Metal GPU acceleration pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal # Build base version with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # Or with Vulkan acceleration CMAKE_ARGS="-DLLAMA_VULKAN=on" pip install llama-cpp-python # Or with Kompute acceleration CMAKE_ARGS="-DLLAMA_KOMPUTE=on" pip install llama-cpp-python # Or with SYCL acceleration CMAKE_ARGS="-DLLAMA_SYCL=on -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_CUDA=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama from llama_cpp.llama_grammar import LlamaGrammar import json # Chat Completion API grammar = LlamaGrammar.from_json_schema(json.dumps({ "type": "array", "items": { "type": "object", "required": [ "name", "arguments" ], "properties": { "name": { "type": "string" }, "arguments": { "type": "object" } } } })) llm = Llama(model_path="./gorilla-openfunctions-v2.IQ3_M.gguf", n_gpu_layers=33, n_ctx=16384) response = llm.create_chat_completion( temperature = 0.0, repeat_penalty = 1.1, messages = [ { "role": "user", "content": "What's the weather like in Oslo and Stockholm?" } ], tools=[{ "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": [ "celsius", "fahrenheit" ] } }, "required": [ "location" ] } } }], grammar = grammar ) print(json.loads(response["choices"][0]["text"])) print(llm.create_chat_completion( temperature = 0.0, repeat_penalty = 1.1, messages = [ { "role": "user", "content": "What's the weather like in Oslo and Stockholm?" }, { # The tool_calls is from the response to the above with tool_choice active "role": "assistant", "content": None, "tool_calls": [ { "id": "call__0_get_current_weather_cmpl-...", "type": "function", "function": { "name": "get_current_weather", "arguments": '{ "location": "Oslo, NO" ,"unit": "celsius"} ' } } ] }, { # The tool_call_id is from tool_calls and content is the result from the function call you made "role": "tool", "content": "20", "tool_call_id": "call__0_get_current_weather_cmpl-..." } ], tools=[{ "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, "unit": { "type": "string", "enum": [ "celsius", "fahrenheit" ] } }, "required": [ "location" ] } } }], #tool_choice={ # "type": "function", # "function": { # "name": "get_current_weather" # } #} )) ``` # Original model card: Gorilla OpenFunctions v2 💡 SoTA for open-source models. On-par with GPT-4. 🚀 Check out the [Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard) 📣 Read more in our [OpenFunctions v2 release blog](https://gorilla.cs.berkeley.edu/blogs/7_open_functions_v2.html) ## Introduction Gorilla OpenFunctions extends Large Language Model(LLM) Chat Completion feature to formulate executable APIs call given natural language instructions and API context. With OpenFunctions v2, we now support: 1. Multiple functions - choose betwen functions 2. Parallel functions - call the same function `N` time with different parameter values 3. Multiple & parallel - both of the above in a single chatcompletion call (one generation) 4. Relevance detection - when chatting, chat. When asked for function, returns a function 5. Python - supports `string, number, boolean, list, tuple, dict` parameter datatypes and `Any` for those not natively supported. 6. JAVA - support for `byte, short, int, float, double, long, boolean, char, Array, ArrayList, Set, HashMap, Hashtable, Queue, Stack, and Any` datatypes. 7. JavaScript - support for `String, Number, Bigint, Boolean, dict (object), Array, Date, and Any` datatypes. 8. REST - native REST support ## Performance | Model | Accuracy | |---|---| |GPT-4-0125-Preview | 83.80% | |Gorilla-openfunctions-v2 | 83.55% | |GPT-3.5-turbo | 81.63% | |Mistral-medium | 79.56% | |Nexusflow Raven-v2 | 54.46% | |GPT-4-0613 | 53.49% | ## Models Available |Model | Functionality| |---|---| |gorilla-openfunctions-v2 | Multiple, parallel, multiple & parallel, relevance detection, Python + JAVA + JS + REST| |gorilla-openfunctions-v1 | Parallel functions, and can choose between functions| |gorilla-openfunctions-v0 | Given a function, and user intent, returns properly formatted json with the right arguments| All of our models are hosted on our Huggingface UC Berkeley gorilla-llm org: [gorilla-openfunctions-v2](https://huggingface.co/gorilla-llm/gorilla-openfunctions-v2), [gorilla-openfunctions-v1](https://huggingface.co/gorilla-llm/gorilla-openfunctions-v1), and [gorilla-openfunctions-v0](https://huggingface.co/gorilla-llm/gorilla-openfunctions-v0). ## Training Gorilla Openfunctions v2 is a 7B parameter model, and is built on top of the [deepseek coder](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5) LLM. Check out [openfunctions-v2 blog](https://gorilla.cs.berkeley.edu/blogs/7_open_functions_v2.html) to learn more about the data composition and some insights into the training process. ## Example Usage (Hosted) 1. OpenFunctions is compatible with OpenAI Functions ```bash !pip install openai==0.28.1 ``` 2. Point to Gorilla hosted servers ```python import openai def get_gorilla_response(prompt="Call me an Uber ride type \"Plus\" in Berkeley at zipcode 94704 in 10 minutes", model="gorilla-openfunctions-v0", functions=[]): openai.api_key = "EMPTY" openai.api_base = "http://luigi.millennium.berkeley.edu:8000/v1" try: completion = openai.ChatCompletion.create( model="gorilla-openfunctions-v2", temperature=0.0, messages=[{"role": "user", "content": prompt}], functions=functions, ) return completion.choices[0] except Exception as e: print(e, model, prompt) ``` 3. Pass the user argument and set of functions, Gorilla OpenFunctions returns a fully formatted json ```python query = "What's the weather like in the two cities of Boston and San Francisco?" functions = [ { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, }, "required": ["location"], }, } ] get_gorilla_response(query, functions=functions) ``` 4. Expected output **NEW** Gorilla returns a readily accessible string **AND** Open-AI compatible JSON. ```python { "index": 0, "message": { "role": "assistant", "content": "get_current_weather(location='Boston, MA'), get_current_weather(location='San Francisco, CA')", "function_call": [ { "name": "get_current_weather", "arguments": { "location": "Boston, MA" } }, { "name": "get_current_weather", "arguments": { "location": "San Francisco, CA" } } ] }, "finish_reason": "stop" } ``` We have retained the string functionality that our community loved from OpenFunctions v1 `get_current_weather(location='Boston, MA'), get_current_weather(location='San Francisco, CA')` above. And Notice the `function_call` key in the JSON to be OpenAI compatible. This is possible in OpenFunctions v2, because we ensure that the output includes the name of the argument and not just the value. This enables us to parse the output into a JSON. In those scenarios where the output is not parsable into JSON, we will always return the function call string. ### End to End Example Run the example code in `[ofv2_hosted.py](https://github.com/ShishirPatil/gorilla/tree/main/openfunctions)` to see how the model works. ```bash python ofv2_hosted.py ``` Expected Output: ```bash (.py3) shishir@dhcp-132-64:~/Work/Gorilla/openfunctions/$ python ofv2_hosted.py -------------------- Function call strings(s): get_current_weather(location='Boston, MA'), get_current_weather(location='San Francisco, CA') -------------------- OpenAI compatible `function_call`: [ JSON: { "name": "get_current_weather", "arguments": { "location": "Boston, MA" } }, JSON: { "name": "get_current_weather", "arguments": { "location": "San Francisco, CA" } }] ``` ## Running OpenFunctions Locally If you want to Run OpenFunctions locally, here is the prompt format that we used: ```python def get_prompt(user_query: str, functions: list = []) -> str: """ Generates a conversation prompt based on the user's query and a list of functions. Parameters: - user_query (str): The user's query. - functions (list): A list of functions to include in the prompt. Returns: - str: The formatted conversation prompt. """ system = "You are an AI programming assistant, utilizing the Gorilla LLM model, developed by Gorilla LLM, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer." if len(functions) == 0: return f"{system}\n### Instruction: <> {user_query}\n### Response: " functions_string = json.dumps(functions) return f"{system}\n### Instruction: <>{functions_string}\n<>{user_query}\### Response: " ``` Further, here is how we format the response: Install the dependencies with: ```bash pip3 install tree_sitter git clone https://github.com/tree-sitter/tree-sitter-java.git git clone https://github.com/tree-sitter/tree-sitter-javascript.git ``` And you can use the following code to format the response: ```python from openfunctions_utils import strip_function_calls, parse_function_call def format_response(response: str): """ Formats the response from the OpenFunctions model. Parameters: - response (str): The response generated by the LLM. Returns: - str: The formatted response. - dict: The function call(s) extracted from the response. """ function_call_dicts = None try: response = strip_function_calls(response) # Parallel function calls returned as a str, list[dict] if len(response) > 1: function_call_dicts = [] for function_call in response: function_call_dicts.append(parse_function_call(function_call)) response = ", ".join(response) # Single function call returned as a str, dict else: function_call_dicts = parse_function_call(response[0]) response = response[0] except Exception as e: # Just faithfully return the generated response str to the user pass return response, function_call_dicts ``` **Note:** Use the `get_prompt` and `format_response` only if you are hosting it Locally. If you are using the Berkeley hosted models through the Chat-completion API, we do this in the backend, so you don't have to do this. The model is supported in Hugging Face 🤗 Transformers and can be run up locally: ## License Gorilla OpenFunctions v2 is distributed under the Apache 2.0 license. This software incorporates elements from the Deepseek model. Consequently, the licensing of Gorilla OpenFunctions v2 adheres to the Apache 2.0 license, with additional terms as outlined in [Appendix A](https://github.com/deepseek-ai/DeepSeek-LLM/blob/6712a86bfb7dd25c73383c5ad2eb7a8db540258b/LICENSE-MODEL) of the Deepseek license. ## Contributing Gorilla is an open source effort from UC Berkeley and we welcome contributors. Please email us your comments, criticism, and questions. More information about the project can be found at [https://gorilla.cs.berkeley.edu/](https://gorilla.cs.berkeley.edu/)