Import from GAIR/DataOrchestra; rename to Orchestrator, update model paths and arXiv link

.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 +1,134 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-1.7B-Base
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- pretraining-data
+- data-curation
+- data-cleaning
+- dataorchestra
+---
+
+# DataOrchestra — Orchestrator Model
+
+## Model Details
+
+| | |
+| --- | --- |
+| Base model | [`Qwen/Qwen3-1.7B-Base`](https://huggingface.co/Qwen/Qwen3-1.7B-Base) |
+| Role | Orchestrator (plan generator) |
+| Input | one pretraining-data chunk (≤ 1024 Qwen3 tokens) |
+| Output | a flat JSON plan (`decision` + NP / SR / PA) |
+| Inference mode | non-thinking, greedy decoding |
+
+
+## Usage
+
+The wire format is a one-line system prompt plus the raw chunk wrapped in `[DOC]` / `[/DOC]`. The model responds with a single JSON plan.
+
+```python
+import json
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL = "DataOrchestra/Orchestrator"
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+model = AutoModelForCausalLM.from_pretrained(MODEL, torch_dtype="auto", device_map="auto")
+
+SYSTEM_PROMPT = "You are an excellent orchestrator for pretraining data cleaning."
+
+
+def plan_for_chunk(chunk: str) -> dict:
+    messages = [
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user", "content": f"[DOC]\n{chunk}\n[/DOC]"},
+    ]
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+        enable_thinking=False,           # orchestrator runs non-thinking
+    )
+    inputs = tokenizer(text, return_tensors="pt").to(model.device)
+    generated = model.generate(
+        **inputs,
+        max_new_tokens=1024,
+        do_sample=False,                 # greedy: temperature 0.0 / top_p 1.0
+    )
+    response = tokenizer.decode(
+        generated[0][inputs.input_ids.shape[1]:], skip_special_tokens=True
+    )
+    return json.loads(response)
+
+
+chunk = (
+    "Home | About | Contact\n\n"
+    "The Pythagorean theorem states that a^2 + b^2 = c^2 for a right triangle. "
+    "It is one of the most fundamental results in geometry.\n\n"
+    "Click here to subscribe to our newsletter!"
+)
+print(json.dumps(plan_for_chunk(chunk), indent=2, ensure_ascii=False))
+```
+
+### Serving with vLLM
+
+For high-throughput curation, serve the model with an OpenAI-compatible endpoint:
+
+```bash
+vllm serve DataOrchestra/Orchestrator --served-model-name DataOrchestra-Orchestrator --trust-remote-code
+```
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")
+resp = client.chat.completions.create(
+    model="DataOrchestra-Orchestrator",
+    messages=[
+        {"role": "system", "content": "You are an excellent orchestrator for pretraining data cleaning."},
+        {"role": "user", "content": "[DOC]\n<your chunk here>\n[/DOC]"},
+    ],
+    temperature=0.0,
+    max_tokens=1024,
+    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
+)
+print(resp.choices[0].message.content)
+```
+
+## Output Schema
+
+The orchestrator returns a flat plan JSON:
+
+```json
+{
+  "decision": "clean",
+  "noise_pruning": true,
+  "surface_rectification": "Remove the navigation header and the newsletter call-to-action; keep the statement of the theorem.",
+  "pedagogical_augmentation": "Add an intuitive explanation of why a^2 + b^2 = c^2 holds, with a worked example."
+}
+```
+
+| Field | Type | Meaning |
+| --- | --- | --- |
+| `decision` | `"drop"` \| `"untouch"` \| `"clean"` | top-level gate; only `clean` triggers the stages below |
+| `noise_pruning` | `bool` | run the NP tool model (whole-line `remove_lines` edits) |
+| `surface_rectification` | `str` \| `null` | if a string, run SR with this chunk-specific instruction; `null` skips |
+| `pedagogical_augmentation` | `str` \| `null` | if a string, run PA with this chunk-specific instruction; `null` skips |
+
+For `drop` / `untouch` decisions, all three stage fields are inert.
+
+
+## Citation
+
+If you find this work useful, please cite:
+
+```bibtex
+@article{dataorchestra2026,
+  title   = {DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data},
+  author  = {Huang, Zhen and Wang, Yikun and Xia, Shijie and Liu, Pengfei},
+  year    = {2026},
+  journal = {arXiv preprint arXiv:2607.24717}
+}
+```

chat_template.jinja

@@ -0,0 +1,13 @@
+{%- if messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>assistant\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "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": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "do_sample": false,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879e21e07f4d54560488538e27b5d97dae9cb54d4baaa5ad765822e38b48c84d
+size 4063515640

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

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": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}