From b1f85dde9abe2f1add428aa2e64f9f04f005bd20 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Mon, 16 Sep 2024 17:33:09 +0100 Subject: [PATCH] huggingface: update rate limit information --- README.md | 4 ++-- src/pull_available_models.py | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 63b83e5..586520d 100644 --- a/README.md +++ b/README.md @@ -108,9 +108,9 @@ This lists various services that provide free access or credits towards API-base Shared Limit HuggingFace Serverless Inference - Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. + Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. Various open models - + 300 requests/hour (with an account) OVH AI Endpoints (Free Alpha)Token expires every 2 weeks.CodeLlama 13B Instruct12 requests/minute Llama 2 13B Chat12 requests/minute Llama 3 70B Instruct12 requests/minute diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 7aa86cb..f435c3b 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -584,9 +584,9 @@ def main(): table += """ HuggingFace Serverless Inference - Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. + Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. Various open models - + 300 requests/hour (with an account) """ for idx, model in enumerate(ovh_models):