The chat_template shipped here was byte-identical to Qwen2.5's, so <think>
blocks were never stripped from earlier assistant turns, enable_thinking was
unavailable and a Qwen2.5 default system prompt was injected.
This is Qwen3's upstream template with the last_query_index prescan removed, so
reasoning is stripped from every prior assistant turn unconditionally. That
keeps rendering monotonic, which append-only KV cache prefilling requires.
quantized duplicated precisions.json, which is authoritative for the
quantized/non-quantized partition. default expressed a per-repository
recommendation nothing consumed: the library resolves its own per-platform
default. Both are gone from the schema.
Adds library_name to the model card, and pipeline_tag where it was missing.
Brings the config and card licenses into agreement, and repairs the variant
declarations that did not match the files actually published here.
Update chat template for strict monotonicity and tool support
