From bb2db8e2c43daf722ddb3725db9264a70cb1747b Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Sun, 4 Aug 2024 09:02:52 +0100 Subject: [PATCH] update groq, add hyperbolic --- README.md | 13 ++++++++++--- src/README_template.md | 10 ++++++++-- src/pull_available_models.py | 8 +++++++- 3 files changed, 25 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 90992a2..6dc7f89 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ This lists various services that provide free access or credits towards API-base -GroqGemma 2 9B Instruct14400 requests/day
15000 tokens/minute +GroqGemma 2 9B Instruct14400 requests/day
15000 tokens/minute Gemma 7B Instruct14400 requests/day
15000 tokens/minute Llama 3 70B14400 requests/day
6000 tokens/minute Llama 3 70B - Groq Tool Use Preview14400 requests/day
15000 tokens/minute @@ -24,6 +24,7 @@ This lists various services that provide free access or credits towards API-base Llama 3 8B - Groq Tool Use Preview14400 requests/day
15000 tokens/minute Llama 3.1 70B14400 requests/day
131072 tokens/minute Llama 3.1 8B14400 requests/day
131072 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 OpenRouterGemma 2 9B Instruct20 requests/minute
200 requests/day @@ -131,6 +132,12 @@ This lists various services that provide free access or credits towards API-base + + Hyperbolic + $10 + + Various open models + Anthropic $5 for 14 days @@ -163,9 +170,9 @@ This lists various services that provide free access or credits towards API-base Unify - $10 + $10 (+$40 for getting into contact) - Routes to other providers, various open models and proprietary models (OpenAI, Anthropic, Mistral, Perplexity) + Routes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc) DeepInfra diff --git a/src/README_template.md b/src/README_template.md index b65a722..d0afbbf 100644 --- a/src/README_template.md +++ b/src/README_template.md @@ -20,6 +20,12 @@ This lists various services that provide free access or credits towards API-base + + Hyperbolic + $10 + + Various open models + Anthropic $5 for 14 days @@ -52,9 +58,9 @@ This lists various services that provide free access or credits towards API-base Unify - $10 + $10 (+$40 for getting into contact) - Routes to other providers, various open models and proprietary models (OpenAI, Anthropic, Mistral, Perplexity) + Routes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc) DeepInfra diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 49a7d6a..9e822ec 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -60,6 +60,7 @@ MODEL_TO_NAME_MAPPING = { "llama3-8b-8192": "Llama 3 8B", "llama3-groq-70b-8192-tool-use-preview": "Llama 3 70B - Groq Tool Use Preview", "llama3-groq-8b-8192-tool-use-preview": "Llama 3 8B - Groq Tool Use Preview", + "llama-guard-3-8b": "Llama Guard 3 8B", "meta-llama/llama-3-8b-instruct:free": "Llama 3 8B Instruct", "meta-llama/llama-3.1-8b-instruct:free": "Llama 3.1 8B Instruct", "microsoft/phi-3-medium-128k-instruct:free": "Phi-3 Medium 128k Instruct", @@ -119,7 +120,12 @@ def get_groq_limits_for_model(model_id): "Authorization": f'Bearer {os.environ["GROQ_API_KEY"]}', "Content-Type": "application/json", }, - json={"model": model_id, "messages": [{"role": "user", "content": "Hi!"}]}, + json={ + "model": model_id, + "messages": [{"role": "user", "content": "Hi!"}], + "stream": True, + }, + stream=True, ) try: r.raise_for_status()