diff options
| -rw-r--r-- | config.example.yaml | 4 | ||||
| -rw-r--r-- | models.yaml | 33 |
2 files changed, 27 insertions, 10 deletions
diff --git a/config.example.yaml b/config.example.yaml index 99db566..40cd311 100644 --- a/config.example.yaml +++ b/config.example.yaml @@ -87,8 +87,8 @@ clients: # supports_function_calling: true # - name: xxxx # Embedding model # type: embedding - # max_input_tokens: 2048 - # max_tokens_per_chunk: 2048 + # max_input_tokens: 200000 + # max_tokens_per_chunk: 2000 # default_chunk_size: 1500 # max_batch_size: 100 # - name: xxxx # Reranker model diff --git a/models.yaml b/models.yaml index 7f3b954..c492a11 100644 --- a/models.yaml +++ b/models.yaml @@ -335,6 +335,8 @@ - name: mistral-large max_input_tokens: 128000 supports_function_calling: true + - name: deepseek-coder-v2 + max_input_tokens: 32768 - name: phi3 max_input_tokens: 128000 supports_function_calling: true @@ -538,6 +540,12 @@ require_max_tokens: true input_price: 0 output_price: 0 + - name: '@hf/thebloke/deepseek-coder-6.7b-instruct-awq' + max_input_tokens: 6144 + max_output_tokens: 2048 + require_max_tokens: true + input_price: 0 + output_price: 0 - name: '@cf/baai/bge-large-en-v1.5' type: embedding input_price: 0 @@ -871,29 +879,29 @@ max_input_tokens: 32000 input_price: 2.7 output_price: 2.7 + supports_function_calling: true - name: meta-llama/Meta-Llama-3.1-70B-Instruct max_input_tokens: 128000 input_price: 0.52 output_price: 0.75 + supports_function_calling: true - name: meta-llama/Meta-Llama-3.1-8B-Instruct max_input_tokens: 128000 input_price: 0.09 output_price: 0.09 + supports_function_calling: true - name: meta-llama/Meta-Llama-3-70B-Instruct max_input_tokens: 8192 input_price: 0.59 output_price: 0.79 - supports_function_calling: true - name: meta-llama/Meta-Llama-3-8B-Instruct max_input_tokens: 8192 input_price: 0.08 output_price: 0.08 - supports_function_calling: true - name: mistralai/Mistral-Nemo-Instruct-2407 max_input_tokens: 128000 input_price: 0.13 output_price: 0.13 - supports_function_calling: true - name: google/gemma-2-27b-it max_input_tokens: 8192 input_price: 0.27 @@ -1119,22 +1127,27 @@ max_input_tokens: 131072 input_price: 3 output_price: 3 + supports_function_calling: true - name: meta-llama/llama-3.1-70b-instruct max_input_tokens: 131072 input_price: 0.75 output_price: 0.75 + supports_function_calling: true - name: meta-llama/llama-3.1-8b-instruct max_input_tokens: 131072 input_price: 0.09 output_price: 0.09 + supports_function_calling: true - name: meta-llama/llama-3-70b-instruct max_input_tokens: 8192 input_price: 0.59 output_price: 0.79 + supports_function_calling: true - name: meta-llama/llama-3-8b-instruct max_input_tokens: 8192 input_price: 0.07 output_price: 0.07 + supports_function_calling: true - name: mistralai/mistral-large max_input_tokens: 128000 input_price: 3 @@ -1183,10 +1196,12 @@ max_input_tokens: 32768 input_price: 0.14 output_price: 0.28 + supports_function_calling: true - name: deepseek/deepseek-coder max_input_tokens: 32768 input_price: 0.14 output_price: 0.28 + supports_function_calling: true - name: perplexity/llama-3.1-sonar-huge-128k-online max_input_tokens: 127072 input_price: 5 @@ -1247,18 +1262,21 @@ max_input_tokens: 131072 input_price: 3 output_price: 9 + supports_function_calling: true - name: meta-llama-3.1-70b-instruct max_input_tokens: 131072 input_price: 0.9 output_price: 0.9 + supports_function_calling: true - name: meta-llama-3.1-8b-instruct max_input_tokens: 131072 input_price: 0.15 output_price: 0.15 - - name: meta-llama-3-70b-instruct - max_input_tokens: 8192 - input_price: 0.9 - output_price: 0.9 + supports_function_calling: true + - name: mistral-nemo-instruct + max_input_tokens: 65536 + input_price: 0.2 + output_price: 0.2 - name: thenlper/gte-large type: embedding input_price: 0.05 @@ -1267,7 +1285,6 @@ 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 |