From 58aa632580093370ef51953e21651442b29b5ca6 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Tue, 27 Aug 2024 15:33:41 +0100 Subject: [PATCH] add vertex ai gemini experimental, hyperbolic llama 3.1 405b base (fp16) --- README.md | 10 +++++++--- src/pull_available_models.py | 9 +++++++-- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index e091267..f510e8c 100644 --- a/README.md +++ b/README.md @@ -68,10 +68,14 @@ This lists various services that provide free access or credits towards API-base embedding-001 1500 requests/min
100 content/batch - Google Cloud Vertex AI - Very stringent payment verification for Google Cloud. + Google Cloud Vertex AI + Very stringent payment verification for Google Cloud. Llama 3.1 405B Instruct Llama 3.1 API Service free during preview.
60 requests/minute + + + Gemini Experimental + Experimental Gemini model. (Not the same as the experimental models on AI Studio)
2 requests/minute glhf.chat (Free Beta) @@ -92,8 +96,8 @@ This lists various services that provide free access or credits towards API-base Various open models Hyperbolic (Free Testing Period)Hermes 3 Llama 3.1 70B200 requests/minute -Hermes 3 Llama 3.1 70B (FP8)200 requests/minute Llama 3 70B Instruct200 requests/minute +Llama 3.1 405B200 requests/minute Llama 3.1 405B Base (FP8)200 requests/minute Llama 3.1 405B Instruct200 requests/minute Llama 3.1 70B Instruct200 requests/minute diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 3c6042a..875c311 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -70,6 +70,7 @@ MODEL_TO_NAME_MAPPING = { "meta-llama/llama-3-8b-instruct:free": "Llama 3 8B Instruct", "meta-llama/llama-3.1-8b-instruct:free": "Llama 3.1 8B Instruct", "meta-llama/meta-llama-3-70b-instruct": "Llama 3 70B Instruct", + "meta-llama/meta-llama-3.1-405b": "Llama 3.1 405B", "meta-llama/meta-llama-3.1-405b-fp8": "Llama 3.1 405B Base (FP8)", "meta-llama/meta-llama-3.1-405b-instruct": "Llama 3.1 405B Instruct", "meta-llama/meta-llama-3.1-70b-instruct": "Llama 3.1 70B Instruct", @@ -489,10 +490,14 @@ def main(): """ table += """ - Google Cloud Vertex AI - Very stringent payment verification for Google Cloud. + Google Cloud Vertex AI + Very stringent payment verification for Google Cloud. Llama 3.1 405B Instruct Llama 3.1 API Service free during preview.
60 requests/minute + + + Gemini Experimental + Experimental Gemini model. (Not the same as the experimental models on AI Studio)
2 requests/minute """ table += """