Update card and sentence-transformers config

README.md

@@ -23,7 +23,9 @@ document, judge whether the skill helps. Fine-tuned from
 Reranks the candidates recalled by
 [skillcorpus-embedding-0.6b](https://huggingface.co/EverMind-AI/skillcorpus-embedding-0.6b).
 Because scoring is one forward pass per (task, skill) pair, run it on a shortlist
-— typically the encoder's top 10–20 — not the whole corpus.
+— typically the encoder's top 20–50 — not the whole corpus. The skill documents
+it was built to score have the schema of
+[skillcorpus-demo-1k](https://huggingface.co/datasets/EverMind-AI/skillcorpus-demo-1k).
 
 | Property | Value |
 |---|---|
@@ -32,6 +34,9 @@ Because scoring is one forward pass per (task, skill) pair, run it on a shortlis
 | Precision | bfloat16 |
 | Output | `P("yes")` in `[0, 1]` |
 
+Requires `transformers>=4.56` (the `dtype=` argument was named `torch_dtype=`
+before that).
+
 ## Usage
 
 The model answers a yes/no question; the relevance score is the softmax over the
@@ -78,21 +83,51 @@ print(score([
     pair(task, "resolve-conflicts", "Resolve git merge conflicts.", "..."),
     pair(task, "sourdough", "Bake sourdough bread.", "..."),
 ]))
-# -> [0.98, 0.01]
+# -> [0.97, 0.01]
 ```
 
+Exact scores shift in the last decimal with dtype and hardware; the ordering is
+what matters.
+
 Two things to keep intact: the `PREFIX` / `SUFFIX` template, since the score is
 read off the final-position logits, and the `<Instruct>` / `<Query>` /
 `<Document>` layout with blank lines between the parts. Truncate the document
 body, not the template.
 
+### Via the chat template
+
+`chat_template.jinja` reproduces exactly the string built above, so you can let
+the tokenizer assemble it instead. It reads three roles — `system` carries the
+instruction (omit it to get the default shown above), `query` the task, and
+`document` the skill:
+
+```python
+prompt = tok.apply_chat_template([
+    {"role": "system",   "content": INSTRUCT},
+    {"role": "query",    "content": task},
+    {"role": "document", "content": "resolve-conflicts | Resolve git merge conflicts. | ..."},
+], tokenize=False)
+```
+
+### Truncation used in training
+
+Beyond the token-level `max_length`, each field was cut to a fixed number of
+**characters** before the prompt was assembled. Matching this keeps inference
+inputs on the same distribution as training:
+
+| field | limit |
+|---|---|
+| skill `description` | 500 chars |
+| skill `body` | 2,000 chars |
+
 ## Intended use
 
 Second-stage reranking over a shortlist recalled by
 [skillcorpus-embedding-0.6b](https://huggingface.co/EverMind-AI/skillcorpus-embedding-0.6b)
 — typically its top 20–50. Scoring is one forward pass per (task, skill) pair,
-so it does not scale to a whole registry. Scores are calibrated per pair;
-compare them within one candidate list, not across different tasks.
+so it does not scale to a whole registry. Treat the output as a ranking signal
+rather than a calibrated probability: compare scores within one candidate list,
+not across different tasks.
 
 ## Citation
 

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -1,11 +1,13 @@
-{%- set instruction = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a web search query, retrieve relevant passages that answer the query") -%}
+{%- set instruction = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a task description, judge whether the skill document is relevant and useful for completing the task") -%}
 {%- set query_text = messages | selectattr("role", "eq", "query") | map(attribute="content") | first -%}
 {%- set document_text = messages | selectattr("role", "eq", "document") | map(attribute="content") | first -%}
 <|im_start|>system
 Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>
 <|im_start|>user
 <Instruct>: {{ instruction }}
+
 <Query>: {{ query_text }}
+
 <Document>: {{ document_text }}<|im_end|>
 <|im_start|>assistant
 <think>

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1,15 +1,240 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
-  "backend": "tokenizers",
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "is_local": true,
+  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
-}
+}