Update card and sentence-transformers config

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

README.md

@@ -1,9 +1,10 @@
 ---
 license: apache-2.0
 base_model: Qwen/Qwen3-Embedding-0.6B
-library_name: transformers
+library_name: sentence-transformers
 pipeline_tag: feature-extraction
 tags:
+  - transformers
   - sentence-similarity
   - retrieval
   - agent-skills
@@ -23,7 +24,9 @@ neighbour. Fine-tuned from
 [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B).
 
 Paired with [skillcorpus-reranker-0.6b](https://huggingface.co/EverMind-AI/skillcorpus-reranker-0.6b),
-which reranks this model's top candidates.
+which reranks this model's top candidates. The skill documents it was built to
+index have the schema of
+[skillcorpus-demo-1k](https://huggingface.co/datasets/EverMind-AI/skillcorpus-demo-1k).
 
 | Property | Value |
 |---|---|
@@ -34,6 +37,9 @@ which reranks this model's top candidates.
 | Pooling | last token |
 | Normalization | L2 |
 
+Requires `transformers>=4.56` (the `dtype=` argument was named `torch_dtype=`
+before that) or `sentence-transformers>=3.0`.
+
 ## Usage
 
 The two sides are encoded asymmetrically — a task description carries an
@@ -80,14 +86,48 @@ query = embed([QUERY_INSTRUCTION + "resolve conflicts after a git merge"])
 docs = embed([doc("resolve-conflicts", "Resolve git merge conflicts.", "..."),
               doc("sourdough", "Bake sourdough bread.", "...")])
 print((query @ docs.T).tolist())
-# -> [[0.74, 0.06]]
+# -> [[0.75, 0.07]]
 ```
 
+Exact scores shift in the last decimal with dtype and hardware; the ordering is
+what matters.
+
+### With sentence-transformers
+
+The repo ships a sentence-transformers configuration (last-token pooling + L2
+normalization, and the query instruction registered as the `query` prompt), so
+this path is equivalent to the code above, up to bf16 noise:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+st = SentenceTransformer("EverMind-AI/skillcorpus-embedding-0.6b")
+q = st.encode(["resolve conflicts after a git merge"], prompt_name="query")
+d = st.encode(["resolve-conflicts | Resolve git merge conflicts. | ...",
+               "sourdough | Bake sourdough bread. | ..."])
+print(st.similarity(q, d))
+```
+
+Pass `prompt_name="query"` for tasks and nothing for skill documents — that is
+the asymmetry above, applied for you.
+
+### Truncation used in training
+
+Beyond the token-level `max_length`, each field was cut to a fixed number of
+**characters** before the strings were assembled. Matching this keeps inference
+inputs on the same distribution as training:
+
+| field | limit |
+|---|---|
+| task description (after the instruction prefix) | 1,500 chars |
+| skill `description` | 500 chars |
+| skill `body` | 8,000 chars |
+
 ## Intended use
 
 First-stage retrieval over a large skill registry: encode the registry offline,
-encode each incoming task online, take the top K by cosine similarity (K=20 or
-50 is typical), then rerank with
+encode each incoming task online, take the top K by cosine similarity (K in the
+20–50 range is typical), then rerank that shortlist with
 [skillcorpus-reranker-0.6b](https://huggingface.co/EverMind-AI/skillcorpus-reranker-0.6b).
 Not a generative model — it produces embeddings, not answers.
 

config_sentence_transformers.json

@@ -0,0 +1,8 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a task description, retrieve the most relevant skill document that would help an agent complete the task\nQuery:",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 2048,
+  "do_lower_case": false
+}