diff options
| author | sigoden <sigoden@gmail.com> | 2024-09-02 10:38:53 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-09-02 10:38:53 +0800 |
| commit | dc78636129427111e8949dcb0160aee15c0f3e91 (patch) | |
| tree | ab4ea2661830e61911cebfc16c7ac41216f9f392 /models.yaml | |
| parent | e39498e340a192077ec64d14c72470cd99716a71 (diff) | |
| download | aichat-dc78636129427111e8949dcb0160aee15c0f3e91.tar.gz | |
feat: add huggingface client (#822)
Diffstat (limited to 'models.yaml')
| -rw-r--r-- | models.yaml | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/models.yaml b/models.yaml index 3b30583..1a02da1 100644 --- a/models.yaml +++ b/models.yaml @@ -543,6 +543,24 @@ 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 # - https://replicate.com/docs/reference/http#create-a-prediction-using-an-official-model |