[MIGRATION]

README.md

@@ -1,7 +1,5 @@
-[![Multi-Modality](agorabanner.png)](https://discord.com/servers/agora-999382051935506503)
 
 # Swarms Models
 
 [![Join our Discord](https://img.shields.io/badge/Discord-Join%20our%20server-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/agora-999382051935506503) [![Subscribe on YouTube](https://img.shields.io/badge/YouTube-Subscribe-red?style=for-the-badge&logo=youtube&logoColor=white)](https://www.youtube.com/@kyegomez3242) [![Connect on LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/kye-g-38759a207/) [![Follow on X.com](https://img.shields.io/badge/X.com-Follow-1DA1F2?style=for-the-badge&logo=x&logoColor=white)](https://x.com/kyegomezb)
 
-

swarm_models/base_multimodal_model.py

@@ -30,7 +30,7 @@ class BaseMultiModalModel(BaseStructure):
         retries (Optional[int], optional): Retries. Defaults to 3.
 
     Examples:
-        >>> from swarms_models.base_multimodal_model import BaseMultiModalModel
+        >>> from swarm_models.base_multimodal_model import BaseMultiModalModel
         >>> model = BaseMultiModalModel()
         >>> model.run("Generate a summary of this text")
         >>> model.run("Generate a summary of this text", "https://www.google.com/images/branding/googlelogo/2x/googlelogo_color_272x92dp.png")

swarm_models/base_tts.py

@@ -2,7 +2,7 @@
 from abc import abstractmethod
 from typing import Optional
 
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 
 class BaseTTSModel(BaseLLM):

swarm_models/base_ttv.py

@@ -5,7 +5,7 @@
 
 from diffusers.utils import export_to_video
 
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 
 class BaseTextToVideo(BaseLLM):

swarm_models/cog_vlm.py

@@ -13,7 +13,7 @@
     TextIteratorStreamer,
 )
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 from swarms.utils.loguru_logger import logger
 
 MODEL_PATH = "THUDM/cogvlm-chat-hf"

swarm_models/fuyu.py

@@ -7,7 +7,7 @@
     FuyuProcessor,
 )
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class Fuyu(BaseMultiModalModel):
@@ -26,7 +26,7 @@ class Fuyu(BaseMultiModalModel):
 
 
     Examples:
-    >>> from swarms_models import Fuyu
+    >>> from swarm_models import Fuyu
     >>> model = Fuyu()
     >>> model.run("Hello, world!", "https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG")
     """

swarm_models/gemini.py

@@ -5,7 +5,7 @@
 from dotenv import load_dotenv
 from PIL import Image
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 try:
     import google.generativeai as genai
@@ -62,7 +62,7 @@ class Gemini(BaseMultiModalModel):
 
 
     Examples:
-        >>> from swarms_models import Gemini
+        >>> from swarm_models import Gemini
         >>> gemini = Gemini()
         >>> gemini.run(
                 task="A dog",

swarm_models/gpt4_vision_api.py

@@ -9,7 +9,7 @@
 from dotenv import load_dotenv
 from termcolor import colored
 from swarms.utils.loguru_logger import logger
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 # Load environment variables
 load_dotenv()
@@ -47,7 +47,7 @@ class GPT4VisionAPI(BaseMultiModalModel):
 
     Examples:
     ---------
-    >>> from swarms_models import GPT4VisionAPI
+    >>> from swarm_models import GPT4VisionAPI
     >>> llm = GPT4VisionAPI()
     >>> task = "What is the color of the object?"
     >>> img = "https://i.imgur.com/2M2ZGwC.jpeg"
@@ -188,7 +188,7 @@ def video_prompt(self, frames):
         Examples
         --------
 
-        >>> from swarms_models import GPT4VisionAPI
+        >>> from swarm_models import GPT4VisionAPI
         >>> llm = GPT4VisionAPI()
         >>> video = "video.mp4"
         >>> base64_frames = llm.process_video(video)

swarm_models/huggingface.py

@@ -11,7 +11,7 @@
     BitsAndBytesConfig,
 )
 
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 
 class HuggingfaceLLM(BaseLLM):

swarm_models/huggingface_pipeline.py

@@ -3,7 +3,7 @@
 import torch
 from termcolor import colored
 
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 from transformers.pipelines import pipeline
 
 

swarm_models/idefics.py

@@ -4,7 +4,7 @@
 from termcolor import colored
 from transformers import AutoProcessor, IdeficsForVisionText2Text
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 def autodetect_device():
@@ -55,7 +55,7 @@ class Idefics(BaseMultiModalModel):
 
     # Usage
     ```
-    from swarms_models import idefics
+    from swarm_models import idefics
 
     model = idefics()
 

swarm_models/kosmos_two.py

@@ -2,7 +2,7 @@
 from PIL import Image
 from transformers import AutoModelForVision2Seq, AutoProcessor
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 # utils

swarm_models/layoutlm_document_qa.py

@@ -5,7 +5,7 @@
 
 from transformers import pipeline
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class LayoutLMDocumentQA(BaseMultiModalModel):
@@ -17,7 +17,7 @@ class LayoutLMDocumentQA(BaseMultiModalModel):
         task (str, optional): [description]. Defaults to "document-question-answering".
 
     Usage:
-    >>> from swarms_models import LayoutLMDocumentQA
+    >>> from swarm_models import LayoutLMDocumentQA
     >>> model = LayoutLMDocumentQA()
     >>> out = model("What is the total amount?", "path/to/img.png")
     >>> print(out)

swarm_models/llama3_hosted.py

@@ -1,6 +1,6 @@
 import requests
 import json
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 
 class llama3Hosted(BaseLLM):

swarm_models/llama_function_caller.py

@@ -12,7 +12,7 @@
     BitsAndBytesConfig,
     TextStreamer,
 )
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 
 class LlamaFunctionCaller(BaseLLM):

swarm_models/llava.py

@@ -5,7 +5,7 @@
 from PIL import Image
 from transformers import AutoProcessor, LlavaForConditionalGeneration
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class LavaMultiModal(BaseMultiModalModel):

swarm_models/model_router.py

@@ -1,40 +1,40 @@
 from typing import List, Union
 
-from swarms_models.base_embedding_model import BaseEmbeddingModel
-from swarms_models.base_llm import BaseLLM
-from swarms_models.base_multimodal_model import BaseMultiModalModel
-from swarms_models.fuyu import Fuyu  # noqa: E402
-from swarms_models.gpt4_vision_api import GPT4VisionAPI  # noqa: E402
-from swarms_models.huggingface import HuggingfaceLLM  # noqa: E402
-from swarms_models.idefics import Idefics  # noqa: E402
-from swarms_models.kosmos_two import Kosmos  # noqa: E402
-from swarms_models.layoutlm_document_qa import LayoutLMDocumentQA
-from swarms_models.llama3_hosted import llama3Hosted
-from swarms_models.llava import LavaMultiModal  # noqa: E402
-from swarms_models.nougat import Nougat  # noqa: E402
-from swarms_models.openai_embeddings import OpenAIEmbeddings
-from swarms_models.openai_function_caller import OpenAIFunctionCaller
-from swarms_models.openai_tts import OpenAITTS  # noqa: E402
-from swarms_models.palm import GooglePalm as Palm  # noqa: E402
-from swarms_models.popular_llms import Anthropic as Anthropic
-from swarms_models.popular_llms import (
+from swarm_models.base_embedding_model import BaseEmbeddingModel
+from swarm_models.base_llm import BaseLLM
+from swarm_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.fuyu import Fuyu  # noqa: E402
+from swarm_models.gpt4_vision_api import GPT4VisionAPI  # noqa: E402
+from swarm_models.huggingface import HuggingfaceLLM  # noqa: E402
+from swarm_models.idefics import Idefics  # noqa: E402
+from swarm_models.kosmos_two import Kosmos  # noqa: E402
+from swarm_models.layoutlm_document_qa import LayoutLMDocumentQA
+from swarm_models.llama3_hosted import llama3Hosted
+from swarm_models.llava import LavaMultiModal  # noqa: E402
+from swarm_models.nougat import Nougat  # noqa: E402
+from swarm_models.openai_embeddings import OpenAIEmbeddings
+from swarm_models.openai_function_caller import OpenAIFunctionCaller
+from swarm_models.openai_tts import OpenAITTS  # noqa: E402
+from swarm_models.palm import GooglePalm as Palm  # noqa: E402
+from swarm_models.popular_llms import Anthropic as Anthropic
+from swarm_models.popular_llms import (
     AzureOpenAILLM as AzureOpenAI,
 )
-from swarms_models.popular_llms import (
+from swarm_models.popular_llms import (
     CohereChat as Cohere,
 )
-from swarms_models.popular_llms import FireWorksAI, OctoAIChat
-from swarms_models.popular_llms import (
+from swarm_models.popular_llms import FireWorksAI, OctoAIChat
+from swarm_models.popular_llms import (
     OpenAIChatLLM as OpenAIChat,
 )
-from swarms_models.popular_llms import (
+from swarm_models.popular_llms import (
     OpenAILLM as OpenAI,
 )
-from swarms_models.popular_llms import ReplicateChat as Replicate
-from swarms_models.qwen import QwenVLMultiModal  # noqa: E402
-from swarms_models.sampling_params import SamplingParams
-from swarms_models.together import TogetherLLM  # noqa: E402
-from swarms_models.vilt import Vilt  # noqa: E402
+from swarm_models.popular_llms import ReplicateChat as Replicate
+from swarm_models.qwen import QwenVLMultiModal  # noqa: E402
+from swarm_models.sampling_params import SamplingParams
+from swarm_models.together import TogetherLLM  # noqa: E402
+from swarm_models.vilt import Vilt  # noqa: E402
 from swarms.structs.base_structure import BaseStructure
 from swarms.utils.loguru_logger import logger
 

swarm_models/moondream_mm.py

@@ -1,7 +1,7 @@
 from PIL import Image
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class MoonDream(BaseMultiModalModel):

swarm_models/nougat.py

@@ -26,7 +26,7 @@ class Nougat:
         max_new_tokens: int, default=30
 
     Usage:
-    >>> from swarms_models.nougat import Nougat
+    >>> from swarm_models.nougat import Nougat
     >>> nougat = Nougat()
     >>> nougat("path/to/image.png")
 

swarm_models/open_dalle.py

@@ -3,7 +3,7 @@
 import torch
 from diffusers import AutoPipelineForText2Image
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class OpenDalle(BaseMultiModalModel):
@@ -15,7 +15,7 @@ class OpenDalle(BaseMultiModalModel):
         device (str): The device to be used for computation. Defaults to "cuda".
 
     Examples:
-        >>> from swarms_models.open_dalle import OpenDalle
+        >>> from swarm_models.open_dalle import OpenDalle
         >>> od = OpenDalle()
         >>> od.run("A picture of a cat")
 

swarm_models/open_router.py

@@ -1,4 +1,4 @@
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 from pydantic import BaseModel
 from typing import List, Dict
 import openai

swarm_models/openai_function_caller.py

@@ -2,7 +2,7 @@
 from pydantic import BaseModel
 import os
 from swarms.utils.loguru_logger import logger
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 from typing import List
 
 

swarm_models/openai_tts.py

@@ -5,7 +5,7 @@
 import requests
 from dotenv import load_dotenv
 
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 try:
     import wave
@@ -41,7 +41,7 @@ class OpenAITTS(BaseLLM):
 
 
     Examples:
-    >>> from swarms_models.openai_tts import OpenAITTS
+    >>> from swarm_models.openai_tts import OpenAITTS
     >>> tts = OpenAITTS(
     ...     model_name = "tts-1-1106",
     ...     proxy_url = "https://api.openai.com/v1/audio/speech",

swarm_models/qwen.py

@@ -4,7 +4,7 @@
 from PIL import Image
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 @dataclass

swarm_models/together.py

@@ -5,7 +5,7 @@
 import requests
 from dotenv import load_dotenv
 
-from swarms_models.base_llm import BaseLLM
+from swarm_models.base_llm import BaseLLM
 
 # Load environment variables
 load_dotenv()
@@ -41,7 +41,7 @@ class TogetherLLM(BaseLLM):
 
     Examples:
     ---------
-    >>> from swarms_models import GPT4VisionAPI
+    >>> from swarm_models import GPT4VisionAPI
     >>> llm = GPT4VisionAPI()
     >>> task = "What is the color of the object?"
     >>> img = "https://i.imgur.com/2M2ZGwC.jpeg"

swarm_models/vilt.py

@@ -2,7 +2,7 @@
 from PIL import Image
 from transformers import ViltForQuestionAnswering, ViltProcessor
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class Vilt(BaseMultiModalModel):

swarm_models/vip_llava.py

@@ -8,7 +8,7 @@
     VipLlavaForConditionalGeneration,
 )
 
-from swarms_models.base_multimodal_model import BaseMultiModalModel
+from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 
 class VipLlavaMultiModal(BaseMultiModalModel):

swarm_models/zeroscope.py

@@ -33,7 +33,7 @@ class ZeroscopeTTV:
             Performs forward pass on the input task and returns the path of the generated video.
 
     Examples:
-        >>> from swarms_models
+        >>> from swarm_models
         >>> zeroscope = ZeroscopeTTV()
         >>> task = "A person is walking on the street."
         >>> video_path = zeroscope(task)