From b52715cce155245c4a4cb20d0ea84463ca502d34 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Sun, 13 Oct 2024 00:25:44 +0100 Subject: [PATCH] all: add thousand separators --- README.md | 68 ++++++++++++++++++------------------ src/README_template.md | 2 +- src/pull_available_models.py | 14 ++++---- 3 files changed, 42 insertions(+), 42 deletions(-) diff --git a/README.md b/README.md index cef2e09..36cee25 100644 --- a/README.md +++ b/README.md @@ -20,25 +20,25 @@ This lists various services that provide free access or credits towards API-base -GroqDistil Whisper Large v37200 audio-seconds/minute
2000 requests/day -Gemma 2 9B Instruct14400 requests/day
15000 tokens/minute -Gemma 7B Instruct14400 requests/day
15000 tokens/minute -LLaVA 1.5 7B14400 requests/day
30000 tokens/minute -Llama 3 70B14400 requests/day
6000 tokens/minute -Llama 3 70B - Groq Tool Use Preview14400 requests/day
15000 tokens/minute -Llama 3 8B14400 requests/day
30000 tokens/minute -Llama 3 8B - Groq Tool Use Preview14400 requests/day
15000 tokens/minute -Llama 3.1 70B14400 requests/day
20000 tokens/minute -Llama 3.1 8B14400 requests/day
20000 tokens/minute -Llama 3.2 11B (Text Only)7000 requests/day
7000 tokens/minute -Llama 3.2 11B Vision7000 requests/day
7000 tokens/minute -Llama 3.2 1B7000 requests/day
7000 tokens/minute -Llama 3.2 3B7000 requests/day
7000 tokens/minute -Llama 3.2 90B (Text Only)7000 requests/day
7000 tokens/minute -Llama Guard 3 8B14400 requests/day
15000 tokens/minute -Mixtral 8x7B14400 requests/day
5000 tokens/minute -Whisper Large v37200 audio-seconds/minute
2000 requests/day -Whisper Large v3 Turbo7200 audio-seconds/minute
2000 requests/day +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 +LLaVA 1.5 7B14,400 requests/day
30,000 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 +Llama 3 8B - Groq Tool Use Preview14,400 requests/day
15,000 tokens/minute +Llama 3.1 70B14,400 requests/day
20,000 tokens/minute +Llama 3.1 8B14,400 requests/day
20,000 tokens/minute +Llama 3.2 11B (Text Only)7,000 requests/day
7,000 tokens/minute +Llama 3.2 11B Vision7,000 requests/day
7,000 tokens/minute +Llama 3.2 1B7,000 requests/day
7,000 tokens/minute +Llama 3.2 3B7,000 requests/day
7,000 tokens/minute +Llama 3.2 90B (Text Only)7,000 requests/day
7,000 tokens/minute +Llama Guard 3 8B14,400 requests/day
15,000 tokens/minute +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 OpenRouterGemma 2 9B Instruct20 requests/minute
200 requests/day Hermes 3 Llama 3.1 405B20 requests/minute
200 requests/day Liquid LFM 40B20 requests/minute
200 requests/day @@ -62,35 +62,35 @@ This lists various services that provide free access or credits towards API-base Google AI Studio Data is used for training (when used outside of the UK/CH/EEA/EU). Gemini 1.5 Flash - 1000000 tokens/minute
1500 requests/day
15 requests/minute + 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute Gemini 1.5 Flash (Experimental) - 1000000 tokens/minute
1500 requests/day
5 requests/minute + 1,000,000 tokens/minute
1,500 requests/day
5 requests/minute Gemini 1.5 Flash-8B - 1000000 tokens/minute
1500 requests/day
15 requests/minute + 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute Gemini 1.5 Flash-8B (Experimental) - 1000000 tokens/minute
1500 requests/day
15 requests/minute + 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute Gemini 1.5 Pro - 32000 tokens/minute
50 requests/day
2 requests/minute + 32,000 tokens/minute
50 requests/day
2 requests/minute Gemini 1.5 Pro (Experimental) - 1000000 tokens/minute
50 requests/day
2 requests/minute + 1,000,000 tokens/minute
50 requests/day
2 requests/minute Gemini 1.0 Pro - 32000 tokens/minute
1500 requests/day
15 requests/minute + 32,000 tokens/minute
1,500 requests/day
15 requests/minute text-embedding-004 - 150 batch requests/minute
1500 requests/minute
100 content/batch + 150 batch requests/minute
1,500 requests/minute
100 content/batch embedding-001 @@ -113,12 +113,12 @@ This lists various services that provide free access or credits towards API-base Mistral (Codestral) Currently free to use, monthly subscription based, requires phone number verification. Codestral - 30 requests/minute
2000 requests/day + 30 requests/minute
2,000 requests/day HuggingFace Serverless Inference Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. Various open models - 1000 requests/day (with an account) + 1,000 requests/day (with an account) SambaNova Cloud @@ -144,11 +144,11 @@ This lists various services that provide free access or credits towards API-base Cerebras Waitlist
Free tier restricted to 8K context Llama 3.1 8B - 30 requests/minute
60000 tokens/minute
900 requests/hour
1000000 tokens/hour
14400 requests/day
1000000 tokens/day + 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day Llama 3.1 70B - 30 requests/minute
60000 tokens/minute
900 requests/hour
1000000 tokens/hour
14400 requests/day
1000000 tokens/day + 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day GitHub ModelsWaitlist
Rate limits dependent on Copilot subscription tierAI21-Jamba-Instruct Cohere Command R Cohere Command R+ @@ -183,7 +183,7 @@ This lists various services that provide free access or credits towards API-base Mistral 7B Instruct12 requests/minute Mixtral 8x22B Instruct12 requests/minute Mixtral 8x7B Instruct12 requests/minute -Cloudflare Workers AI10000 tokens/dayDeepseek Coder 6.7B Base (AWQ) +Cloudflare Workers AI10,000 tokens/dayDeepseek Coder 6.7B Base (AWQ) Deepseek Coder 6.7B Instruct (AWQ) Deepseek Math 7B Instruct Discolm German 7B v1 (AWQ) @@ -230,7 +230,7 @@ This lists various services that provide free access or credits towards API-base Free for 2024 Cohere - 20 requests/min
1000 requests/month + 20 requests/min
1,000 requests/month Command-R Shared Limit @@ -305,7 +305,7 @@ This lists various services that provide free access or credits towards API-base NVIDIA NIM - 1000 API calls + 1,000 API calls Various open models diff --git a/src/README_template.md b/src/README_template.md index 99b2daa..dc51bd2 100644 --- a/src/README_template.md +++ b/src/README_template.md @@ -50,7 +50,7 @@ This lists various services that provide free access or credits towards API-base NVIDIA NIM - 1000 API calls + 1,000 API calls Various open models diff --git a/src/pull_available_models.py b/src/pull_available_models.py index a1cc06e..cbd6cf8 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -499,7 +499,7 @@ def get_human_limits(model): if "limits" not in model: return "" limits = model["limits"] - return "
".join([f"{value} {key}" for key, value in limits.items()]) + return "
".join([f"{value:,} {key}" for key, value in limits.items()]) def main(): @@ -620,14 +620,14 @@ def main(): Mistral (Codestral) Currently free to use, monthly subscription based, requires phone number verification. Codestral - 30 requests/minute
2000 requests/day + 30 requests/minute
2,000 requests/day """ table += """ HuggingFace Serverless Inference Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. Various open models - 1000 requests/day (with an account) + 1,000 requests/day (with an account) """ table += """ @@ -657,11 +657,11 @@ def main(): Cerebras Waitlist
Free tier restricted to 8K context Llama 3.1 8B - 30 requests/minute
60000 tokens/minute
900 requests/hour
1000000 tokens/hour
14400 requests/day
1000000 tokens/day + 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day Llama 3.1 70B - 30 requests/minute
60000 tokens/minute
900 requests/hour
1000000 tokens/hour
14400 requests/day
1000000 tokens/day + 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day """ for idx, model in enumerate(github_models): @@ -690,7 +690,7 @@ def main(): table += 'Cloudflare Workers AI' table += '' table += '' - table += '10000 tokens/day' + table += '10,000 tokens/day' table += '' table += f"{model['name']}" table += "" @@ -705,7 +705,7 @@ def main(): table += """ Cohere - 20 requests/min
1000 requests/month + 20 requests/min
1,000 requests/month Command-R Shared Limit