diff options
Diffstat (limited to 'g4f/local')
| -rw-r--r-- | g4f/local/__init__.py | 21 | ||||
| -rw-r--r-- | g4f/local/_engine.py | 42 | ||||
| -rw-r--r-- | g4f/local/_models.py | 86 | ||||
| -rw-r--r-- | g4f/local/models/model-here | 1 |
4 files changed, 11 insertions, 139 deletions
diff --git a/g4f/local/__init__.py b/g4f/local/__init__.py index c9d3d74a..117cd48d 100644 --- a/g4f/local/__init__.py +++ b/g4f/local/__init__.py @@ -1,17 +1,19 @@ -from ..typing import Union, Iterator, Messages -from ..stubs import ChatCompletion, ChatCompletionChunk -from ._engine import LocalProvider -from ._models import models -from ..client import iter_response, filter_none, IterResponse +from __future__ import annotations + +from ..typing import Union, Messages +from ..locals.provider import LocalProvider +from ..locals.models import get_models +from ..client.client import iter_response, filter_none +from ..client.types import IterResponse class LocalClient(): def __init__(self, **kwargs) -> None: self.chat: Chat = Chat(self) - + @staticmethod def list_models(): - return list(models.keys()) - + return list(get_models()) + class Completions(): def __init__(self, client: LocalClient): self.client: LocalClient = client @@ -25,8 +27,7 @@ class Completions(): max_tokens: int = None, stop: Union[list[str], str] = None, **kwargs - ) -> Union[ChatCompletion, Iterator[ChatCompletionChunk]]: - + ) -> IterResponse: stop = [stop] if isinstance(stop, str) else stop response = LocalProvider.create_completion( model, messages, stream, diff --git a/g4f/local/_engine.py b/g4f/local/_engine.py deleted file mode 100644 index 917de16c..00000000 --- a/g4f/local/_engine.py +++ /dev/null @@ -1,42 +0,0 @@ -import os - -from gpt4all import GPT4All -from ._models import models - -class LocalProvider: - @staticmethod - def create_completion(model, messages, stream, **kwargs): - if model not in models: - raise ValueError(f"Model '{model}' not found / not yet implemented") - - model = models[model] - model_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'models/') - full_model_path = os.path.join(model_dir, model['path']) - - if not os.path.isfile(full_model_path): - print(f"Model file '{full_model_path}' not found.") - download = input(f'Do you want to download {model["path"]} ? [y/n]') - - if download in ['y', 'Y']: - GPT4All.download_model(model['path'], model_dir) - else: - raise ValueError(f"Model '{model['path']}' not found.") - - model = GPT4All(model_name=model['path'], - #n_threads=8, - verbose=False, - allow_download=False, - model_path=model_dir) - - system_template = next((message['content'] for message in messages if message['role'] == 'system'), - 'A chat between a curious user and an artificial intelligence assistant.') - - prompt_template = 'USER: {0}\nASSISTANT: ' - conversation = '\n'.join(f"{msg['role'].upper()}: {msg['content']}" for msg in messages) + "\nASSISTANT: " - - with model.chat_session(system_template, prompt_template): - if stream: - for token in model.generate(conversation, streaming=True): - yield token - else: - yield model.generate(conversation)
\ No newline at end of file diff --git a/g4f/local/_models.py b/g4f/local/_models.py deleted file mode 100644 index ec36fe41..00000000 --- a/g4f/local/_models.py +++ /dev/null @@ -1,86 +0,0 @@ -models = { - "mistral-7b": { - "path": "mistral-7b-openorca.gguf2.Q4_0.gguf", - "ram": "8", - "prompt": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n", - "system": "<|im_start|>system\nYou are MistralOrca, a large language model trained by Alignment Lab AI. For multi-step problems, write out your reasoning for each step.\n<|im_end|>" - }, - "mistral-7b-instruct": { - "path": "mistral-7b-instruct-v0.1.Q4_0.gguf", - "ram": "8", - "prompt": "[INST] %1 [/INST]", - "system": None - }, - "gpt4all-falcon": { - "path": "gpt4all-falcon-newbpe-q4_0.gguf", - "ram": "8", - "prompt": "### Instruction:\n%1\n### Response:\n", - "system": None - }, - "orca-2": { - "path": "orca-2-13b.Q4_0.gguf", - "ram": "16", - "prompt": None, - "system": None - }, - "wizardlm-13b": { - "path": "wizardlm-13b-v1.2.Q4_0.gguf", - "ram": "16", - "prompt": None, - "system": None - }, - "nous-hermes-llama2": { - "path": "nous-hermes-llama2-13b.Q4_0.gguf", - "ram": "16", - "prompt": "### Instruction:\n%1\n### Response:\n", - "system": None - }, - "gpt4all-13b-snoozy": { - "path": "gpt4all-13b-snoozy-q4_0.gguf", - "ram": "16", - "prompt": None, - "system": None - }, - "mpt-7b-chat": { - "path": "mpt-7b-chat-newbpe-q4_0.gguf", - "ram": "8", - "prompt": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n", - "system": "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>" - }, - "orca-mini-3b": { - "path": "orca-mini-3b-gguf2-q4_0.gguf", - "ram": "4", - "prompt": "### User:\n%1\n### Response:\n", - "system": "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n" - }, - "replit-code-3b": { - "path": "replit-code-v1_5-3b-newbpe-q4_0.gguf", - "ram": "4", - "prompt": "%1", - "system": None - }, - "starcoder": { - "path": "starcoder-newbpe-q4_0.gguf", - "ram": "4", - "prompt": "%1", - "system": None - }, - "rift-coder-7b": { - "path": "rift-coder-v0-7b-q4_0.gguf", - "ram": "8", - "prompt": "%1", - "system": None - }, - "all-MiniLM-L6-v2": { - "path": "all-MiniLM-L6-v2-f16.gguf", - "ram": "1", - "prompt": None, - "system": None - }, - "mistral-7b-german": { - "path": "em_german_mistral_v01.Q4_0.gguf", - "ram": "8", - "prompt": "USER: %1 ASSISTANT: ", - "system": "Du bist ein hilfreicher Assistent. " - } -}
\ No newline at end of file diff --git a/g4f/local/models/model-here b/g4f/local/models/model-here deleted file mode 100644 index 945c9b46..00000000 --- a/g4f/local/models/model-here +++ /dev/null @@ -1 +0,0 @@ -.
\ No newline at end of file |