From 30b6f3843ee4c9c25ae03eb8537df3fc454e2f08 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Wed, 11 Dec 2024 20:58:16 +0000 Subject: [PATCH] update --- README.md | 18 +++++++++++++----- src/pull_available_models.py | 17 +++++++++++++---- 2 files changed, 26 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index a7b3484..51bac33 100644 --- a/README.md +++ b/README.md @@ -25,7 +25,7 @@ This lists various services that provide free access or credits towards API-base GroqDistil Whisper Large v37,200 audio-seconds/minute
2,000 requests/day Gemma 2 9B Instruct14,400 requests/day
15,000 tokens/minute -Gemma 7B Instruct14,400 requests/day
15,000 tokens/minute +Gemma 7B Instruct (Deprecated)14,400 requests/day
15,000 tokens/minute Llama 3 70B14,400 requests/day
6,000 tokens/minute Llama 3 70B - Groq Tool Use Preview14,400 requests/day
15,000 tokens/minute Llama 3 8B14,400 requests/day
30,000 tokens/minute @@ -42,7 +42,8 @@ This lists various services that provide free access or credits towards API-base Mixtral 8x7B14,400 requests/day
5,000 tokens/minute Whisper Large v37,200 audio-seconds/minute
2,000 requests/day Whisper Large v3 Turbo7,200 audio-seconds/minute
2,000 requests/day -OpenRouter20 requests/minute
200 requests/dayGemini Experimental 1114 +OpenRouter20 requests/minute
200 requests/dayGemini 2.0 Flash Experimental +Gemini Experimental 1114 Gemini Experimental 1206 Gemma 2 9B Instruct Llama 3 8B Instruct @@ -62,8 +63,12 @@ This lists various services that provide free access or credits towards API-base Toppy M 7B Zephyr 7B Beta - Google AI Studio - Data is used for training (when used outside of the UK/CH/EEA/EU). + Google AI Studio + Data is used for training (when used outside of the UK/CH/EEA/EU). + Gemini 2.0 Flash + 4,000,000 tokens/minute
10 requests/minute + + Gemini 1.5 Flash 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute @@ -270,9 +275,12 @@ This lists various services that provide free access or credits towards API-base Llama 3.2 90B Vision Instruct Llama 3.2 API Service free during preview.
30 requests/minute + + Gemini 2.0 Flash Experimental + Experimental Gemini model.
10 requests/minute + Gemini Flash Experimental - Experimental Gemini model.
10 requests/minute Gemini Pro Experimental diff --git a/src/pull_available_models.py b/src/pull_available_models.py index da6acb5..6424582 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -52,7 +52,7 @@ MODEL_TO_NAME_MAPPING = { "@hf/thebloke/zephyr-7b-beta-awq": "Zephyr 7B Beta (AWQ)", "codellama-13b-instruct-hf": "CodeLlama 13B Instruct", "distil-whisper-large-v3-en": "Distil Whisper Large v3", - "gemma-7b-it": "Gemma 7B Instruct", + "gemma-7b-it": "Gemma 7B Instruct (Deprecated)", "gemma2-9b-it": "Gemma 2 9B Instruct", "google/gemma-2-9b-it:free": "Gemma 2 9B Instruct", "google/gemma-7b-it:free": "Gemma 7B Instruct", @@ -156,6 +156,7 @@ MODEL_TO_NAME_MAPPING = { "llama3.1-nemotron-70b-instruct-fp8": "Llama 3.1 Nemotron 70B Instruct (FP8)", "llama-3.3-70b-specdec": "Llama 3.3 70B (Speculative Decoding)", "@cf/meta/llama-3.3-70b-instruct-fp8-fast": "Llama 3.3 70B Instruct (FP8)", + "google/gemini-2.0-flash-exp:free": "Gemini 2.0 Flash Experimental", } @@ -189,6 +190,7 @@ OPENROUTER_IGNORED_MODELS = { 'google/learnlm-1.5-pro-experimental:free', 'google/gemini-exp-1114:free' 'google/gemini-exp-1206:free' + 'google/gemini-2.0-flash-exp:free' } # Ignore gemini experimental free models because rate limits mean they are unusable. @@ -632,8 +634,12 @@ def main(): table += "\n" table += f""" - Google AI Studio - Data is used for training (when used outside of the UK/CH/EEA/EU). + Google AI Studio + Data is used for training (when used outside of the UK/CH/EEA/EU). + Gemini 2.0 Flash + {get_human_limits({"limits": gemini_models["gemini-2.0-flash-exp"]})} + + Gemini 1.5 Flash {get_human_limits({"limits": gemini_models["gemini-1.5-flash"]})} @@ -811,9 +817,12 @@ def main(): Llama 3.2 90B Vision Instruct Llama 3.2 API Service free during preview.
30 requests/minute + + Gemini 2.0 Flash Experimental + Experimental Gemini model.
10 requests/minute + Gemini Flash Experimental - Experimental Gemini model.
10 requests/minute Gemini Pro Experimental