From 5300a4c9b3795ce44da56a706236a1ab55ccf5b7 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Wed, 15 May 2024 21:00:56 -0700 Subject: [PATCH] fix model prices --- ...odel_prices_and_context_window_backup.json | 54 +++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e181e0ef32..ff9194578c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2967,6 +2967,24 @@ "litellm_provider": "ollama", "mode": "completion" }, + "ollama/llama3": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat" + }, + "ollama/llama3:70b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat" + }, "ollama/mistral": { "max_tokens": 8192, "max_input_tokens": 8192, @@ -2976,6 +2994,42 @@ "litellm_provider": "ollama", "mode": "completion" }, + "ollama/mistral-7B-Instruct-v0.1": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat" + }, + "ollama/mistral-7B-Instruct-v0.2": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat" + }, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat" + }, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "ollama", + "mode": "chat" + }, "ollama/codellama": { "max_tokens": 4096, "max_input_tokens": 4096,