diff options
Diffstat (limited to 'g4f/Provider/Cloudflare.py')
| -rw-r--r-- | g4f/Provider/Cloudflare.py | 104 |
1 files changed, 21 insertions, 83 deletions
diff --git a/g4f/Provider/Cloudflare.py b/g4f/Provider/Cloudflare.py index e78bbcd0..8fb37bef 100644 --- a/g4f/Provider/Cloudflare.py +++ b/g4f/Provider/Cloudflare.py @@ -1,15 +1,18 @@ from __future__ import annotations +from aiohttp import ClientSession import asyncio import json import uuid import cloudscraper from typing import AsyncGenerator + from ..typing import AsyncResult, Messages from .base_provider import AsyncGeneratorProvider, ProviderModelMixin from .helper import format_prompt class Cloudflare(AsyncGeneratorProvider, ProviderModelMixin): + label = "Cloudflare AI" url = "https://playground.ai.cloudflare.com" api_endpoint = "https://playground.ai.cloudflare.com/api/inference" working = True @@ -17,97 +20,43 @@ class Cloudflare(AsyncGeneratorProvider, ProviderModelMixin): supports_system_message = True supports_message_history = True - default_model = '@cf/meta/llama-3.1-8b-instruct' - models = [ - '@cf/deepseek-ai/deepseek-math-7b-instruct', # Specific answer - - - '@cf/thebloke/discolm-german-7b-v1-awq', - - - '@cf/tiiuae/falcon-7b-instruct', # Specific answer - - - '@hf/google/gemma-7b-it', - - + default_model = '@cf/meta/llama-3.1-8b-instruct-awq' + models = [ '@cf/meta/llama-2-7b-chat-fp16', '@cf/meta/llama-2-7b-chat-int8', '@cf/meta/llama-3-8b-instruct', '@cf/meta/llama-3-8b-instruct-awq', - default_model, '@hf/meta-llama/meta-llama-3-8b-instruct', - '@cf/meta/llama-3.1-8b-instruct-awq', + default_model, '@cf/meta/llama-3.1-8b-instruct-fp8', - '@cf/meta/llama-3.2-11b-vision-instruct', + '@cf/meta/llama-3.2-1b-instruct', - '@cf/meta/llama-3.2-3b-instruct', - '@cf/mistral/mistral-7b-instruct-v0.1', '@hf/mistral/mistral-7b-instruct-v0.2', - '@cf/openchat/openchat-3.5-0106', - - '@cf/microsoft/phi-2', - - '@cf/qwen/qwen1.5-0.5b-chat', - '@cf/qwen/qwen1.5-1.8b-chat', - '@cf/qwen/qwen1.5-14b-chat-awq', - '@cf/qwen/qwen1.5-7b-chat-awq', - - '@cf/defog/sqlcoder-7b-2', # Specific answer - - '@cf/tinyllama/tinyllama-1.1b-chat-v1.0', + '@cf/qwen/qwen1.5-7b-chat-awq', - '@cf/fblgit/una-cybertron-7b-v2-bf16', + '@cf/defog/sqlcoder-7b-2', ] model_aliases = { - "german-7b-v1": "@cf/thebloke/discolm-german-7b-v1-awq", - - - "gemma-7b": "@hf/google/gemma-7b-it", - - "llama-2-7b": "@cf/meta/llama-2-7b-chat-fp16", "llama-2-7b": "@cf/meta/llama-2-7b-chat-int8", "llama-3-8b": "@cf/meta/llama-3-8b-instruct", "llama-3-8b": "@cf/meta/llama-3-8b-instruct-awq", - "llama-3-8b": "@cf/meta/llama-3.1-8b-instruct", "llama-3-8b": "@hf/meta-llama/meta-llama-3-8b-instruct", "llama-3.1-8b": "@cf/meta/llama-3.1-8b-instruct-awq", "llama-3.1-8b": "@cf/meta/llama-3.1-8b-instruct-fp8", - "llama-3.1-8b": "@cf/meta/llama-3.1-8b-instruct-fp8", - "llama-3.2-11b": "@cf/meta/llama-3.2-11b-vision-instruct", "llama-3.2-1b": "@cf/meta/llama-3.2-1b-instruct", - "llama-3.2-3b": "@cf/meta/llama-3.2-3b-instruct", - - "mistral-7b": "@cf/mistral/mistral-7b-instruct-v0.1", - "mistral-7b": "@hf/mistral/mistral-7b-instruct-v0.2", - - - "openchat-3.5": "@cf/openchat/openchat-3.5-0106", - - - "phi-2": "@cf/microsoft/phi-2", - - - "qwen-1.5-0.5b": "@cf/qwen/qwen1.5-0.5b-chat", - "qwen-1.5-1.8b": "@cf/qwen/qwen1.5-1.8b-chat", - "qwen-1.5-14b": "@cf/qwen/qwen1.5-14b-chat-awq", "qwen-1.5-7b": "@cf/qwen/qwen1.5-7b-chat-awq", - - "tinyllama-1.1b": "@cf/tinyllama/tinyllama-1.1b-chat-v1.0", - - - "cybertron-7b": "@cf/fblgit/una-cybertron-7b-v2-bf16", + #"sqlcoder-7b": "@cf/defog/sqlcoder-7b-2", } @classmethod @@ -125,8 +74,7 @@ class Cloudflare(AsyncGeneratorProvider, ProviderModelMixin): model: str, messages: Messages, proxy: str = None, - max_tokens: str = 2048, - stream: bool = True, + max_tokens: int = 2048, **kwargs ) -> AsyncResult: model = cls.get_model(model) @@ -154,19 +102,19 @@ class Cloudflare(AsyncGeneratorProvider, ProviderModelMixin): scraper = cloudscraper.create_scraper() - prompt = format_prompt(messages) data = { "messages": [ - {"role": "system", "content": "You are a helpful assistant"}, - {"role": "user", "content": prompt} + {"role": "user", "content": format_prompt(messages)} ], "lora": None, "model": model, "max_tokens": max_tokens, - "stream": stream + "stream": True } max_retries = 3 + full_response = "" + for attempt in range(max_retries): try: response = scraper.post( @@ -181,32 +129,22 @@ class Cloudflare(AsyncGeneratorProvider, ProviderModelMixin): if response.status_code == 403: await asyncio.sleep(2 ** attempt) continue - + response.raise_for_status() for line in response.iter_lines(): if line.startswith(b'data: '): if line == b'data: [DONE]': + if full_response: + yield full_response break try: - content = json.loads(line[6:].decode('utf-8'))['response'] - yield content + content = json.loads(line[6:].decode('utf-8')) + if 'response' in content and content['response'] != '</s>': + yield content['response'] except Exception: continue break except Exception as e: if attempt == max_retries - 1: raise - - @classmethod - async def create_async( - cls, - model: str, - messages: Messages, - proxy: str = None, - **kwargs - ) -> str: - full_response = "" - async for response in cls.create_async_generator(model, messages, proxy, **kwargs): - full_response += response - return full_response |