From 12bf4346ec9441b4a7fabac24d0901bf186bc708 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Fri, 19 Apr 2024 14:34:38 -0700 Subject: [PATCH 1/2] feat - add llama3 on groq --- ...odel_prices_and_context_window_backup.json | 20 +++++++++++++++++++ model_prices_and_context_window.json | 20 +++++++++++++++++++ 2 files changed, 40 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index eedcaa4932..113f9413fd 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -735,6 +735,26 @@ "mode": "chat", "supports_function_calling": true }, + "groq/llama3-8b-8192": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000010, + "output_cost_per_token": 0.00000010, + "litellm_provider": "groq", + "mode": "chat", + "supports_function_calling": true + }, + "groq/llama3-70b-8192": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000064, + "output_cost_per_token": 0.00000080, + "litellm_provider": "groq", + "mode": "chat", + "supports_function_calling": true + }, "groq/mixtral-8x7b-32768": { "max_tokens": 32768, "max_input_tokens": 32768, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index eedcaa4932..113f9413fd 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -735,6 +735,26 @@ "mode": "chat", "supports_function_calling": true }, + "groq/llama3-8b-8192": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000010, + "output_cost_per_token": 0.00000010, + "litellm_provider": "groq", + "mode": "chat", + "supports_function_calling": true + }, + "groq/llama3-70b-8192": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000064, + "output_cost_per_token": 0.00000080, + "litellm_provider": "groq", + "mode": "chat", + "supports_function_calling": true + }, "groq/mixtral-8x7b-32768": { "max_tokens": 32768, "max_input_tokens": 32768, From e8de984b389510956dee2b5291912924aeaba776 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Fri, 19 Apr 2024 14:34:45 -0700 Subject: [PATCH 2/2] docs - add groq llama3 --- docs/my-website/docs/providers/groq.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/my-website/docs/providers/groq.md b/docs/my-website/docs/providers/groq.md index 8443387a5f..da453c3ceb 100644 --- a/docs/my-website/docs/providers/groq.md +++ b/docs/my-website/docs/providers/groq.md @@ -48,6 +48,8 @@ We support ALL Groq models, just set `groq/` as a prefix when sending completion | Model Name | Function Call | |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| llama3-8b-8192 | `completion(model="groq/llama3-8b-8192", messages)` | +| llama3-70b-8192 | `completion(model="groq/llama3-70b-8192", messages)` | | llama2-70b-4096 | `completion(model="groq/llama2-70b-4096", messages)` | | mixtral-8x7b-32768 | `completion(model="groq/mixtral-8x7b-32768", messages)` | | gemma-7b-it | `completion(model="groq/gemma-7b-it", messages)` |