Update README.md

README.md

@@ -10,17 +10,11 @@ datasets:
 
 <img src='cheap.png' width='700'>
 
-
-**A 4B-parameter Qwen model distilled from Tongyi DeepResearch-30B A3B**, optimized for web-scale “deep research” tasks and plug-and-play inference with **[Alibaba-NLP/DeepResearch](https://github.com/Alibaba-NLP/DeepResearch)**.
-
 [![Model](https://img.shields.io/badge/HF-Model-blue)](https://huggingface.co/your-username/your-model-name)
 [![License](https://img.shields.io/badge/License-Apache--2.0-green)](#license)
 [![Dataset](https://img.shields.io/badge/Dataset-CheapResearch--DS--33k-orange)](https://huggingface.co/datasets/cheapresearch/CheapResearch-DS-33k)
 
-
----
-
-## TL;DR
+**A 4B-parameter Qwen model distilled from Tongyi DeepResearch-30B A3B**, optimized for web-scale “deep research” tasks and inference with **[Alibaba-NLP/DeepResearch](https://github.com/Alibaba-NLP/DeepResearch)**.
 
 * **Base**: Qwen 4B (dense)
 * **Teacher**: Tongyi DeepResearch 30B A3B (MoE)
@@ -40,7 +34,6 @@ datasets:
 
 * **Primary dataset**: [`cheapresearch/CheapResearch-DS-33k`](https://huggingface.co/datasets/cheapresearch/CheapResearch-DS-33k)
 
-
 ---
 
 ## Inference with Alibaba-NLP/DeepResearch (Recommended)
@@ -65,22 +58,16 @@ Edit the config to add this model
 MODEL_PATH=cheapresearch/CheapResearch-4B-Thinking
 ```
 
-> ⚠️ **Note**: Use a **search-enabled** profile in DeepResearch so the model can browse and cite sources. Disable “reasoning suppression” features—this student is trained to produce compact but explicit research traces.
-
 ### Hardware notes
 
-* **Single 16–24GB GPU** is enough for 4B FP16; FP8/INT4 quantization allows smaller VRAM.
+* **Single 12–16GB GPU** is enough for 4B FP16; FP8/INT4 quantization allows smaller VRAM. If you quantize, the summary model can be local as well.
 
 ---
 
 ## Evaluation 
 
-| Benchmark            |               Metric | CheapResearch      (4B) | Tongyi DeepResearch (30B A3B) | Notes                           |
-| -------------------- | -------------------: | -----------: | ----------------: | ------------------------------- |
-| HLE textonly 200 @1    |              Correctness (o4) |            — |                 — | With HLE keyword filtering to prevent cheating     |
-| SimpleQA @1 | Win-Rate vs Baseline |            Correctness (o4) |                 — |  With SimpleQA keyword filtering to prevent cheating             |
-
-
+<img src='hle.png' width='700'>
+<img src='simpleqa.png' width='700'>
 
 ## Acknowledgements