From 3bd9a1b7a8f0fd6a7c37d8ad9d45ad44dc779c53 Mon Sep 17 00:00:00 2001 From: Daniel Bichuetti Date: Thu, 23 May 2024 20:19:46 -0300 Subject: [PATCH 1/3] Update model_prices_and_context_window.json This adds some new models from Anyscale --- model_prices_and_context_window.json | 45 ++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index bede36764..0ea1b8f09 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3396,6 +3396,15 @@ "mode": "chat", "supports_function_calling": true }, + "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 0.00000090, + "output_cost_per_token": 0.00000090, + "litellm_provider": "anyscale", + "mode": "chat", + }, "anyscale/HuggingFaceH4/zephyr-7b-beta": { "max_tokens": 16384, "max_input_tokens": 16384, @@ -3405,6 +3414,15 @@ "litellm_provider": "anyscale", "mode": "chat" }, + "anyscale/google/gemma-7b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000015, + "output_cost_per_token": 0.00000015, + "litellm_provider": "anyscale", + "mode": "chat" + }, "anyscale/meta-llama/Llama-2-7b-chat-hf": { "max_tokens": 4096, "max_input_tokens": 4096, @@ -3441,6 +3459,33 @@ "litellm_provider": "anyscale", "mode": "chat" }, + "anyscale/codellama/CodeLlama-70b-Instruct-hf": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000001, + "litellm_provider": "anyscale", + "mode": "chat" + }, + "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000015, + "output_cost_per_token": 0.00000015, + "litellm_provider": "anyscale", + "mode": "chat" + }, + "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000100, + "output_cost_per_token": 0.00000100, + "litellm_provider": "anyscale", + "mode": "chat" + }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "max_tokens": 3072, "max_input_tokens": 3072, From a086088dc70478a8d99be5ec5a1a2749e0b11916 Mon Sep 17 00:00:00 2001 From: Daniel Bichuetti Date: Thu, 23 May 2024 20:24:39 -0300 Subject: [PATCH 2/3] Remove extra char --- model_prices_and_context_window.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 0ea1b8f09..87abec72d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3403,7 +3403,7 @@ "input_cost_per_token": 0.00000090, "output_cost_per_token": 0.00000090, "litellm_provider": "anyscale", - "mode": "chat", + "mode": "chat" }, "anyscale/HuggingFaceH4/zephyr-7b-beta": { "max_tokens": 16384, From 7fdb5aeb24d9193c659de2fbf37e285816e01992 Mon Sep 17 00:00:00 2001 From: Daniel Bichuetti Date: Thu, 23 May 2024 20:43:20 -0300 Subject: [PATCH 3/3] Add source + support_function_calling tag --- model_prices_and_context_window.json | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 87abec72d..b18f8bf61 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3384,9 +3384,10 @@ "output_cost_per_token": 0.00000015, "litellm_provider": "anyscale", "mode": "chat", - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1" }, - "anyscale/Mixtral-8x7B-Instruct-v0.1": { + "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, @@ -3394,7 +3395,8 @@ "output_cost_per_token": 0.00000015, "litellm_provider": "anyscale", "mode": "chat", - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1" }, "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { "max_tokens": 65536, @@ -3403,7 +3405,9 @@ "input_cost_per_token": 0.00000090, "output_cost_per_token": 0.00000090, "litellm_provider": "anyscale", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1" }, "anyscale/HuggingFaceH4/zephyr-7b-beta": { "max_tokens": 16384, @@ -3421,7 +3425,8 @@ "input_cost_per_token": 0.00000015, "output_cost_per_token": 0.00000015, "litellm_provider": "anyscale", - "mode": "chat" + "mode": "chat", + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" }, "anyscale/meta-llama/Llama-2-7b-chat-hf": { "max_tokens": 4096, @@ -3466,7 +3471,8 @@ "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "litellm_provider": "anyscale", - "mode": "chat" + "mode": "chat", + "source" : "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" }, "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { "max_tokens": 8192, @@ -3475,7 +3481,8 @@ "input_cost_per_token": 0.00000015, "output_cost_per_token": 0.00000015, "litellm_provider": "anyscale", - "mode": "chat" + "mode": "chat", + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" }, "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { "max_tokens": 8192, @@ -3484,7 +3491,8 @@ "input_cost_per_token": 0.00000100, "output_cost_per_token": 0.00000100, "litellm_provider": "anyscale", - "mode": "chat" + "mode": "chat", + "source" : "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "max_tokens": 3072,