Commit History
-
Align chat template `enable_thinking` default with generation_config.json and the model card
Verified signatureOne-line change proposing that the template's `enable_thinking` default match the other artifacts in this repo. Three things here say reasoning is on by default: 1. `generation_config.json`: `"default_chat_template_kwargs": {"enable_thinking": true}` 2. The model card: *"Reasoning is on by default; pass `enable_thinking=False` to skip the `<think>` block."* 3. `poolside/Laguna-S-2.1`'s template already uses `default(true)`. But `chat_template.jinja` has `{%- set enable_thinking = enable_thinking | default(false) -%}`. This is invisible on vLLM if the server passes `--default-chat-template-kwargs` as the model card instructs. Stacks without that mechanism read the template default directly, TensorRT-LLM doesn't consume `default_chat_template_kwargs`, so a request omitting `chat_template_kwargs` renders a thinking-*off* prompt while every other artifact says thinking is on, and the reasoning parser missclassifies the response. Context: NVIDIA/TensorRT-LLM#17146.6addec1
-
fix(rope): YaRN attention_factor is (0.1*ln(factor)+1)*attn_factor, not the bare multiplier
Verified signature2bf8a4a
-
Use chat_template.jinja as the single source: drop the {% include %} chat_template field from tokenizer_config.json
Verified signature4f8aa29
-
Update README.md (#8)
- Update README.md (7ba72ace8d6fcf5b2524c1696c0a106988a190f3) Co-authored-by: Jimmy Shong <Jiminator@users.noreply.huggingface.co>5bb2892
-
Update README.md (#7)
- Update README.md (96a4a04ac5eee6c3b1e84d8603862404593b38ed) Co-authored-by: Jimmy Shong <Jiminator@users.noreply.huggingface.co>2f697c8 -
small self-contained fixes
Verified signaturee836636 -
initial commit
Co-authored-by: Jiminator <Jiminator@users.noreply.huggingface.co>9dd7749