diff options
Diffstat (limited to 'models.yaml')
| -rw-r--r-- | models.yaml | 63 |
1 files changed, 62 insertions, 1 deletions
diff --git a/models.yaml b/models.yaml index 5a79454..7f3b954 100644 --- a/models.yaml +++ b/models.yaml @@ -546,7 +546,7 @@ max_batch_size: 100 # Links: -# - https://huggingface.co/models?inference=warm&pipeline_tag=text-generation&other=text-generation-inference&sort=trending +# - https://huggingface.co/models?other=text-generation-inference # - https://huggingface.co/docs/text-generation-inference/en/reference/api_reference - platform: huggingface models: @@ -1266,6 +1266,67 @@ default_chunk_size: 1000 max_batch_size: 100 +# Links +# - https://siliconflow.cn/zh-cn/models +# - https://siliconflow.cn/zh-cn/maaspricing +# - https://docs.siliconflow.cn/reference/chat-completions-3 +- platform: siliconflow + models: + - name: Qwen/Qwen2-72B-Instruct + max_input_tokens: 32768 + input_price: 0 + output_price: 0 + - name: meta-llama/Meta-Llama-3.1-405B-Instruct + max_input_tokens: 32768 + input_price: 2.94 + output_price: 2.94 + - name: meta-llama/Meta-Llama-3.1-70B-Instruct + max_input_tokens: 32768 + input_price: 0.578 + output_price: 0.578 + - name: meta-llama/Meta-Llama-3.1-8B-Instruct + max_input_tokens: 32768 + input_price: 0 + output_price: 0 + - name: google/gemma-2-27b-it + max_input_tokens: 8192 + input_price: 0.176 + output_price: 0.176 + - name: google/gemma-2-9b-it + max_input_tokens: 8192 + input_price: 0 + output_price: 0 + - name: deepseek-ai/DeepSeek-V2-Chat + max_input_tokens: 32768 + input_price: 0.186 + output_price: 0.186 + - name: deepseek-ai/DeepSeek-Coder-V2-Instruct + max_input_tokens: 32768 + input_price: 0.186 + output_price: 0.186 + - name: BAAI/bge-large-en-v1.5 + type: embedding + input_price: 0 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: BAAI/bge-large-zh-v1.5 + type: embedding + input_price: 0 + max_tokens_per_chunk: 512 + default_chunk_size: 1000 + max_batch_size: 100 + - name: BAAI/bge-m3 + type: embedding + input_price: 0 + max_tokens_per_chunk: 8192 + default_chunk_size: 2000 + max_batch_size: 100 + - name: BAAI/bge-reranker-v2-m3 + type: reranker + max_input_tokens: 8192 + input_price: 0 + # Links: # - https://docs.together.ai/docs/inference-models # - https://docs.together.ai/docs/embedding-models |