diff options
Diffstat (limited to 'models.yaml')
| -rw-r--r-- | models.yaml | 64 |
1 files changed, 32 insertions, 32 deletions
diff --git a/models.yaml b/models.yaml index ccb0c60..be4ecc3 100644 --- a/models.yaml +++ b/models.yaml @@ -33,17 +33,17 @@ type: embedding max_input_tokens: 8191 default_chunk_size: 3000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: text-embedding-3-small type: embedding max_input_tokens: 8191 default_chunk_size: 3000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: text-embedding-ada-002 type: embedding max_input_tokens: 8191 default_chunk_size: 3000 - max_concurrent_chunks: 100 + max_batch_size: 100 - platform: gemini # docs: @@ -77,7 +77,7 @@ type: embedding max_input_tokens: 2048 default_chunk_size: 1500 - max_concurrent_chunks: 5 + max_batch_size: 5 - platform: claude # docs: @@ -176,12 +176,12 @@ type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 96 + max_batch_size: 96 - name: embed-multilingual-v3.0 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 96 + max_batch_size: 96 - name: rerank-english-v3.0 type: rerank max_input_tokens: 4096 @@ -307,12 +307,12 @@ type: embedding max_input_tokens: 3072 default_chunk_size: 2000 - max_concurrent_chunks: 5 + max_batch_size: 5 - name: text-multilingual-embedding-002 type: embedding max_input_tokens: 3072 default_chunk_size: 2000 - max_concurrent_chunks: 5 + max_batch_size: 5 - platform: vertexai-claude # docs: @@ -460,12 +460,12 @@ type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: '@cf/baai/bge-large-en-v1.5' type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - platform: replicate # docs: @@ -578,7 +578,7 @@ type: embedding max_input_tokens: 2048 default_chunk_size: 1500 - max_concurrent_chunks: 25 + max_batch_size: 25 - platform: moonshot # docs: @@ -721,12 +721,12 @@ type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 30 + max_batch_size: 30 - name: thenlper/gte-large type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 30 + max_batch_size: 30 - platform: deepinfra # docs: @@ -773,52 +773,52 @@ type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: BAAI/bge-base-en-v1.5 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: BAAI/bge-m3 type: embedding max_input_tokens: 8192 default_chunk_size: 2000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: intfloat/e5-base-v2 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: intfloat/e5-large-v2 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: intfloat/multilingual-e5-large type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: sentence-transformers/all-MiniLM-L6-v2 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: sentence-transformers/paraphrase-MiniLM-L6-v2 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: thenlper/gte-base type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: thenlper/gte-large type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - platform: fireworks # docs: @@ -876,22 +876,22 @@ type: embedding max_input_tokens: 8192 default_chunk_size: 1500 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: WhereIsAI/UAE-Large-V1 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: thenlper/gte-large type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: thenlper/gte-base type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - platform: openrouter # docs: @@ -1072,7 +1072,7 @@ type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - platform: together # docs: @@ -1108,19 +1108,19 @@ max_input_tokens: 32768 input_price: 0.9 output_price: 0.9 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: WhereIsAI/UAE-Large-V1 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: BAAI/bge-large-en-v1.5 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100 + max_batch_size: 100 - name: BAAI/bge-base-en-v1.5 type: embedding max_input_tokens: 512 default_chunk_size: 1000 - max_concurrent_chunks: 100
\ No newline at end of file + max_batch_size: 100
\ No newline at end of file |