refactor - use consistent file naming convention AI21/ -> ai21 (#7090)

* fix refactor - use consistent file naming convention

* ci/cd run again

* fix naming structure

litellm/__init__.py

@@ -1065,8 +1065,8 @@ from .llms.predibase import PredibaseConfig
 from .llms.replicate import ReplicateConfig
 from .llms.cohere.completion import CohereConfig
 from .llms.clarifai import ClarifaiConfig
-from .llms.AI21.completion import AI21Config
-from .llms.AI21.chat import AI21ChatConfig
+from .llms.ai21.completion import AI21Config
+from .llms.ai21.chat import AI21ChatConfig
 from .llms.together_ai.chat import TogetherAIConfig
 from .llms.cloudflare import CloudflareConfig
 from .llms.palm import PalmConfig
@@ -1158,7 +1158,7 @@ nvidiaNimEmbeddingConfig = NvidiaNimEmbeddingConfig()
 
 from .llms.cerebras.chat import CerebrasConfig
 from .llms.sambanova.chat import SambanovaConfig
-from .llms.AI21.chat import AI21ChatConfig
+from .llms.ai21.chat import AI21ChatConfig
 from .llms.fireworks_ai.chat.fireworks_ai_transformation import FireworksAIConfig
 from .llms.fireworks_ai.embed.fireworks_ai_transformation import (
     FireworksAIEmbeddingConfig,

litellm/main.py

@@ -99,7 +99,7 @@ from .llms import (
     replicate,
     vllm,
 )
-from .llms.AI21 import completion as ai21
+from .llms.ai21 import completion as ai21
 from .llms.anthropic.chat import AnthropicChatCompletion
 from .llms.anthropic.completion import AnthropicTextCompletion
 from .llms.azure_ai.chat import AzureAIChatCompletion

tests/llm_translation/test_max_completion_tokens.py

@@ -220,7 +220,7 @@ def test_all_model_configs():
         optional_params={},
     ) == {"max_tokens": 10}
 
-    from litellm.llms.AI21.chat import AI21ChatConfig
+    from litellm.llms.ai21.chat import AI21ChatConfig
 
     assert "max_completion_tokens" in AI21ChatConfig().get_supported_openai_params(
         "jamba-1.5-mini@001"

tests/local_testing/test_completion.py

@@ -24,7 +24,7 @@ from litellm import RateLimitError, Timeout, completion, completion_cost, embedd
 from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
 from litellm.llms.prompt_templates.factory import anthropic_messages_pt
 
-# litellm.num_retries = 3
+# litellm.num_retries=3
 
 litellm.cache = None
 litellm.success_callback = []