From c3ccc4e81945cb0fdb62dd66071f2a57797f31b6 Mon Sep 17 00:00:00 2001 From: H Lohaus Date: Fri, 8 Dec 2023 20:07:28 +0100 Subject: Fix llama2 provider, Update TOC in readme (#1325) --- README.md | 41 +++++++++++++++++++++-------------------- docker-compose.yml | 4 ++-- g4f/Provider/Llama2.py | 16 +++++++--------- 3 files changed, 30 insertions(+), 31 deletions(-) diff --git a/README.md b/README.md index 82e08de5..baf2fb3f 100644 --- a/README.md +++ b/README.md @@ -22,36 +22,37 @@ docker pull hlohaus789/g4f ## 📚 Table of Contents -- [🆕 What's New](#-whats-new) +- [🆕 What's New](#-what-s-new) - [📚 Table of Contents](#-table-of-contents) -- [🛠ī¸ Getting Started](#ī¸-getting-started) - - [Prerequisites:](#prerequisites) - - [Setting up the project:](#setting-up-the-project) +- [🛠ī¸ Getting Started](#-getting-started) + + [Docker container](#docker-container) + - [Quick start](#quick-start) + + [Use python package](#use-python-package) + - [Prerequisites](#prerequisites) - [Install using pypi](#install-using-pypi) - - [or](#or) - - [Setting up with Docker:](#setting-up-with-docker) + + [Docker for Developers](#docker-for-developers) - [💡 Usage](#-usage) - - [The `g4f` Package](#the-g4f-package) - - [ChatCompletion](#chatcompletion) + * [The `g4f` Package](#the-g4f-package) + + [ChatCompletion](#chatcompletion) - [Completion](#completion) - [Providers](#providers) - - [Cookies Required](#cookies-required) + - [Using Browser](#using-browser) - [Async Support](#async-support) - [Proxy and Timeout Support](#proxy-and-timeout-support) - - [Interference openai-proxy API (Use with openai python package)](#interference-openai-proxy-api-use-with-openai-python-package) - - [Run interference API from PyPi package](#run-interference-api-from-pypi-package) - - [Run interference API from repo](#run-interference-api-from-repo) + * [Interference openai-proxy API](#interference-openai-proxy-api-use-with-openai-python-package-) + + [Run interference API from PyPi package](#run-interference-api-from-pypi-package) + + [Run interference API from repo](#run-interference-api-from-repo) - [🚀 Providers and Models](#-providers-and-models) - - [GPT-4](#gpt-4) - - [GPT-3.5](#gpt-35) - - [Other](#other) - - [Models](#models) + * [GPT-4](#gpt-4) + * [GPT-3.5](#gpt-35) + * [Other](#other) + * [Models](#models) - [🔗 Related GPT4Free Projects](#-related-gpt4free-projects) - [🤝 Contribute](#-contribute) - - [Create Provider with AI Tool](#create-provider-with-ai-tool) - - [Create Provider](#create-provider) + + [Create Provider with AI Tool](#create-provider-with-ai-tool) + + [Create Provider](#create-provider) - [🙌 Contributors](#-contributors) -- [Šī¸ Copyright](#ī¸-copyright) +- [Šī¸ Copyright](#-copyright) - [⭐ Star History](#-star-history) - [📄 License](#-license) @@ -70,7 +71,7 @@ docker run -p 8080:80 -p 1337:1337 -p 7900:7900 --shm-size="2g" hlohaus789/g4f:l ``` 3. Open the included client on: [http://localhost:8080/chat/](http://localhost:8080/chat/) or set the api base in your client to: [http://localhost:1337/v1](http://localhost:1337/v1) -4. (Optional) If you need to log in to a provider, you can open the desktop in the container here: http://localhost:7900/?autoconnect=1&resize=scale&password=secret. +4. (Optional) If you need to log in to a provider, you can view the desktop from the container here: http://localhost:7900/?autoconnect=1&resize=scale&password=secret. #### Use python package diff --git a/docker-compose.yml b/docker-compose.yml index 326a3640..66ba8f34 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -7,8 +7,8 @@ services: build: context: . dockerfile: docker/Dockerfile -# volumes: -# - .:/app + volumes: + - .:/app ports: - '8080:80' - '1337:1337' diff --git a/g4f/Provider/Llama2.py b/g4f/Provider/Llama2.py index efe5bdc6..6d0c0a44 100644 --- a/g4f/Provider/Llama2.py +++ b/g4f/Provider/Llama2.py @@ -6,10 +6,9 @@ from ..typing import AsyncResult, Messages from .base_provider import AsyncGeneratorProvider models = { - "meta-llama/Llama-2-7b-chat-hf": {"name": "Llama 2 7B", "version": "d24902e3fa9b698cc208b5e63136c4e26e828659a9f09827ca6ec5bb83014381", "shortened":"7B"}, - "meta-llama/Llama-2-13b-chat-hf": {"name": "Llama 2 13B", "version": "9dff94b1bed5af738655d4a7cbcdcde2bd503aa85c94334fe1f42af7f3dd5ee3", "shortened":"13B"}, - "meta-llama/Llama-2-70b-chat-hf": {"name": "Llama 2 70B", "version": "2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf", "shortened":"70B"}, - "Llava": {"name": "Llava 13B", "version": "6bc1c7bb0d2a34e413301fee8f7cc728d2d4e75bfab186aa995f63292bda92fc", "shortened":"Llava"} + "meta-llama/Llama-2-7b-chat-hf": "meta/llama-2-7b-chat", + "meta-llama/Llama-2-13b-chat-hf": "meta/llama-2-13b-chat", + "meta-llama/Llama-2-70b-chat-hf": "meta/llama-2-70b-chat", } class Llama2(AsyncGeneratorProvider): @@ -26,10 +25,9 @@ class Llama2(AsyncGeneratorProvider): **kwargs ) -> AsyncResult: if not model: - model = "meta-llama/Llama-2-70b-chat-hf" - elif model not in models: - raise ValueError(f"Model are not supported: {model}") - version = models[model]["version"] + model = "meta/llama-2-70b-chat" + elif model in models: + model = models[model] headers = { "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/118.0", "Accept": "*/*", @@ -50,7 +48,7 @@ class Llama2(AsyncGeneratorProvider): prompt = format_prompt(messages) data = { "prompt": prompt, - "version": version, + "model": model, "systemPrompt": kwargs.get("system_message", "You are a helpful assistant."), "temperature": kwargs.get("temperature", 0.75), "topP": kwargs.get("top_p", 0.9), -- cgit v1.2.3