diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 5b11b8360..8009d049d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2255,15 +2255,6 @@ "litellm_provider": "cohere", "mode": "completion" }, - "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0000, - "output_cost_per_token": 0.0000, - "litellm_provider": "replicate", - "mode": "chat" - }, "replicate/meta/llama-2-13b": { "max_tokens": 4096, "max_input_tokens": 4096, diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py index 87efa86be..b538edee5 100644 --- a/litellm/tests/test_completion.py +++ b/litellm/tests/test_completion.py @@ -23,7 +23,7 @@ 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 = [] user_message = "Write a short poem about the sky"