Initial upload

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,113 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-Reranker-0.6B
+library_name: transformers
+pipeline_tag: text-ranking
+tags:
+  - reranker
+  - cross-encoder
+  - retrieval
+  - agent-skills
+  - skill-routing
+  - skillcorpus
+language:
+  - en
+---
+
+# skillcorpus-reranker-0.6b
+
+A cross-encoder for **agent-skill retrieval**: given a task and a candidate skill
+document, judge whether the skill helps. Fine-tuned from
+[Qwen/Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B).
+
+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.
+
+| | |
+|---|---|
+| Parameters | 596M |
+| Layers | 28 |
+| Precision | bfloat16 |
+| Output | `P("yes")` in `[0, 1]` |
+
+## Usage
+
+The model answers a yes/no question; the relevance score is the softmax over the
+`yes` and `no` logits at the final position.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL = "EverMind-AI/skillcorpus-reranker-0.6b"
+tok = AutoTokenizer.from_pretrained(MODEL, padding_side="left")
+model = AutoModelForCausalLM.from_pretrained(MODEL, dtype=torch.bfloat16).cuda().eval()
+
+PREFIX = ('<|im_start|>system\nJudge 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|>\n<|im_start|>user\n')
+SUFFIX = '<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'
+
+YES, NO = tok.convert_tokens_to_ids("yes"), tok.convert_tokens_to_ids("no")
+
+
+def score(pairs, max_length=4096):
+    prompts = [PREFIX + p + SUFFIX for p in pairs]
+    enc = tok(prompts, padding=True, truncation=True,
+              max_length=max_length, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        logits = model(**enc).logits[:, -1, :]
+    pair = torch.stack([logits[:, NO], logits[:, YES]], dim=-1)
+    return torch.softmax(pair, dim=-1)[:, 1].float().tolist()
+
+
+INSTRUCT = ("Given a task description, judge whether the skill document "
+            "is relevant and useful for completing the task")
+
+
+def pair(task, name, description, body):
+    return (f"<Instruct>: {INSTRUCT}\n\n"
+            f"<Query>: {task}\n\n"
+            f"<Document>: {name} | {description} | {body}")
+
+
+task = "resolve conflicts after a git merge"
+print(score([
+    pair(task, "resolve-conflicts", "Resolve git merge conflicts.", "..."),
+    pair(task, "sourdough", "Bake sourdough bread.", "..."),
+]))
+# -> [0.98, 0.01]
+```
+
+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.
+
+## 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.
+
+## Citation
+
+```bibtex
+@article{wang2026skillcorpus,
+  title         = {SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents},
+  author        = {Wang, Yanze and Yao, Pengfei and Sun, Tianyi and Hu, Chuanrui and Xiao, Yan and Luo, Xiaotian and Han, Yunyun and Chen, Yifan and Sun, Jun and Deng, Yafeng},
+  year          = {2026},
+  eprint        = {2607.15557},
+  archivePrefix = {arXiv},
+  url           = {https://arxiv.org/abs/2607.15557}
+}
+```
+
+## License
+
+Apache-2.0, inherited from the base model. Skills in the corpus keep their own
+upstream licenses.

chat_template.jinja

@@ -0,0 +1,15 @@
+{%- 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 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>
+
+</think>
+
+

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669,
+  "rope_theta": 1000000
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faa5f3c2c305cc63b2eaaadb95cbafd50163faf717f0adc15de018fef305a40
+size 1191588280

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a01676060aa035ffebeb8a78c23b1074c2ca1b57082f8839255317a4108309e
+size 11422749

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}