AlpinDale a56bce4c94 fix: remove duplicate assignment in Hermes2ProToolParser преди 1 месец
..
rpc 39b2e83ac3 api: optimize zeromq frontend performance (#951) преди 1 месец
tool_parsers a56bce4c94 fix: remove duplicate assignment in Hermes2ProToolParser преди 1 месец
__init__.py 07aa2a492f upstream: add option to specify tokenizer преди 1 година
api_server.py 313e198557 api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993) преди 1 месец
args.py 313e198557 api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993) преди 1 месец
logits_processors.py 62111fab17 feat: allow serving encoder-decoder models in the API server (#664) преди 5 месеца
protocol.py 0191c5efd1 tools: fix tool calls to more strictly follow OpenAI format (#1003) преди 1 месец
run_batch.py 81fa31bcaf feat: embeddings support for batched OAI endpoint (#676) преди 5 месеца
samplers.json ac82b67f75 feat: naive context shift and various QoL changes (#289) преди 11 месеца
serving_chat.py 7d5feaa037 api: fix logic for deciding if tool parser is used (#1025) преди 1 месец
serving_completions.py 61c7182491 feat: enable prompt logprobs in OpenAI API (#720) преди 5 месеца
serving_embedding.py 0c162c8dad api: use fp32 for base64 embeddings (#919) преди 1 месец
serving_engine.py c5c09720b0 api: log prompt truncation (#940) преди 1 месец
serving_tokenization.py 313e198557 api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993) преди 1 месец