From dc78636129427111e8949dcb0160aee15c0f3e91 Mon Sep 17 00:00:00 2001 From: sigoden Date: Mon, 2 Sep 2024 10:38:53 +0800 Subject: feat: add huggingface client (#822) --- models.yaml | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'models.yaml') diff --git a/models.yaml b/models.yaml index 3b30583..1a02da1 100644 --- a/models.yaml +++ b/models.yaml @@ -542,6 +542,24 @@ default_chunk_size: 1000 max_batch_size: 100 +# Links: +# - https://huggingface.co/models?inference=warm&pipeline_tag=text-generation&other=text-generation-inference&sort=trending +# - https://huggingface.co/docs/text-generation-inference/en/reference/api_reference +- platform: huggingface + models: + - name: meta-llama/Meta-Llama-3-8B-Instruct + max_input_tokens: 8192 + max_output_tokens: 4096 + require_max_tokens: true + input_price: 0 + output_price: 0 + - name: mistralai/Mistral-Nemo-Instruct-2407 + max_input_tokens: 128000 + max_output_tokens: 4096 + require_max_tokens: true + input_price: 0 + output_price: 0 + # Links: # - https://replicate.com/explore # - https://replicate.com/pricing -- cgit v1.2.3