Update README.md

README.md

@@ -14,12 +14,12 @@ license: other
 
 # DECS_7B
 
-DECS_7B is a reasoning-focused causal language model built from `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B` and further trained with a GRPO-style setup on mixed data.
+This is the official model for ICLR 2026 Oral "Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling".
+DECS_7B is a reasoning-focused causal language model built from `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B` and further trained with DECS algorithm, focused on 50% fewer tokens when answering a reasoning-required problem.
 
 ## Model Summary
 
 - Base model: `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`
-- Upload source: local checkpoint `deepscaler_7b_r1_distill_qwen7b_grpo_proc_length_a001_b001_c001_n16_nozeroadv_fm0_constant_dapo_adp_global_step_265`
 - Upload date: `2026-02-24`
 - Recommended use: long-form reasoning and mathematical/problem-solving style generation
 
@@ -75,17 +75,94 @@ print(outputs[0].outputs[0].text)
 - Performance can vary by prompt style and decoding parameters.
 - License and acceptable-use constraints should follow the upstream base model and your deployment policy.
 
-## Privacy Sanitization
 
-Before uploading, local/private metadata is sanitized:
+## Citation
+---
+language:
+- zh
+- en
+pipeline_tag: text-generation
+tags:
+- deepscaler
+- reasoning
+- grpo
+- qwen2
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+license: other
+---
 
-- Absolute local paths are de-identified.
-- Username-like path segments are masked.
-- Path-like fields in config metadata are rewritten to public-safe values.
+# DECS_1.5B
+This is the official model for ICLR 2026 Oral "Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling".
+DECS_1.5B is a reasoning-focused causal language model built from `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B` and further trained with DECS algorithm, focused on 50% fewer tokens when answering a reasoning-required problem.
 
-## Citation
+## Model Summary
+
+- Base model: `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`
+- Upload date: `2026-02-24`
+- Recommended use: long-form reasoning and mathematical/problem-solving style generation
 
-If you use this model, please cite this repository and the upstream base model:
+## Quick Start (Transformers)
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "pixas/DECS_1.5B"
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
 
-- `pixas/DECS_7B`
-- `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`
+messages = [
+    {"role": "user", "content": "Solve: If x^2 - 5x + 6 = 0, what are x values?"}
+]
+prompt = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        temperature=0.6,
+        top_p=0.95,
+    )
+
+new_tokens = outputs[0][inputs["input_ids"].shape[-1]:]
+print(tokenizer.decode(new_tokens, skip_special_tokens=True))
+```
+
+## Quick Start (vLLM)
+
+```python
+from vllm import LLM, SamplingParams
+
+llm = LLM(model="pixas/DECS_1.5B", trust_remote_code=True)
+sampling = SamplingParams(temperature=0.6, top_p=0.95, max_tokens=512)
+prompt = "Please reason step by step: what is 37 * 48?"
+outputs = llm.generate([prompt], sampling_params=sampling)
+print(outputs[0].outputs[0].text)
+```
+
+## Notes
+
+- This model may produce incorrect or unverifiable reasoning. Always validate outputs in high-stakes settings.
+- Performance can vary by prompt style and decoding parameters.
+- License and acceptable-use constraints should follow the upstream base model and your deployment policy.
+
+
+## Citation
+
+If you use this model, please cite our paper:
+```bibtex
+@inproceedings{jiang2026overthinking,
+title={Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling},
+author={Shuyang Jiang and Yusheng Liao and Ya Zhang and Yanfeng Wang and Yu Wang},
+booktitle={The Fourteenth International Conference on Learning Representations},
+year={2026},
+url={https://openreview.net/forum?id=kdeiRledV6}
+}
+```