update readme for better presentation

README.md

@@ -20,11 +20,15 @@ library_name: transformers
 </p>
 
 ## What's New
-- [2025.09.05] **MiniCPM4.1** series are released! This series is a hybrid reasoning model, which can be used in both deep reasoning mode and non-reasoning mode. 🔥🔥🔥
+- [2025.09.05] **MiniCPM4.1** series are released! This series is a hybrid reasoning model with trainable sparse attention, which can be used in both deep reasoning mode and non-reasoning mode. 🔥🔥🔥
 - [2025.06.06] **MiniCPM4** series are released! This model achieves ultimate efficiency improvements while maintaining optimal performance at the same scale! It can achieve over 5x generation acceleration on typical end-side chips! You can find technical report [here](https://arxiv.org/abs/2506.07900).🔥🔥🔥
 
-## MiniCPM4 and MiniCPM4.1 Series
-MiniCPM4 and MiniCPM4.1 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
+## Highlights
+MiniCPM4.1 is highlighted with following features:
+✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks!
+✅ Fast Generation: 3x decoding speedup for reasoning
+✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding
+
 - [MiniCPM4.1-8B](https://huggingface.co/openbmb/MiniCPM4.1-8B): The latest version of MiniCPM4, with 8B parameters, support fusion thinking. (**<-- you are here**)
 - [MiniCPM4.1-8B-GPTQ](https://huggingface.co/openbmb/MiniCPM4.1-8B-GPTQ): MiniCPM4.1-8B in GPTQ format.
 - [MiniCPM4.1-8B-AutoAWQ](https://huggingface.co/openbmb/MiniCPM4.1-8B-AutoAWQ): MiniCPM4.1-8B in AutoAWQ format.
@@ -48,89 +52,29 @@ MiniCPM4 and MiniCPM4.1 series are highly efficient large language models (LLMs)
     - [**MiniCPM4-MCP**](https://huggingface.co/openbmb/MiniCPM4-MCP): Integrates MCP tools to autonomously satisfy user requirements
     </details>
 
-## Introduction
-MiniCPM4 and MiniCPM4.1 are extremely efficient edge-side large model that has undergone efficient optimization across four dimensions: model architecture, learning algorithms, training data, and inference systems, achieving ultimate efficiency improvements.
-
-- 🏗️ **Efficient Model Architecture:**
-  - InfLLM v2 -- Trainable Sparse Attention Mechanism: Adopts a trainable sparse attention mechanism architecture where each token only needs to compute relevance with less than 5% of tokens in 128K long text processing, significantly reducing computational overhead for long texts
-
-- 🧠 **Efficient Learning Algorithms:**
-  - Model Wind Tunnel 2.0 -- Efficient Predictable Scaling: Introduces scaling prediction methods for performance of downstream tasks, enabling more precise model training configuration search
-  - BitCPM -- Ultimate Ternary Quantization: Compresses model parameter bit-width to 3 values, achieving 90% extreme model bit-width reduction
-  - Efficient Training Engineering Optimization: Adopts FP8 low-precision computing technology combined with Multi-token Prediction training strategy
-
-- 📚 **High-Quality Training Data:**
-  - UltraClean -- High-quality Pre-training Data Filtering and Generation: Builds iterative data cleaning strategies based on efficient data verification, open-sourcing high-quality Chinese and English pre-training dataset [UltraFinweb](https://huggingface.co/datasets/openbmb/Ultra-FineWeb)
-  - UltraChat v2 -- High-quality Supervised Fine-tuning Data Generation: Constructs large-scale high-quality supervised fine-tuning datasets covering multiple dimensions including knowledge-intensive data, reasoning-intensive data, instruction-following data, long text understanding data, and tool calling data
-
-- ⚡ **Efficient Inference System:**
-  - CPM.cu -- Lightweight and Efficient CUDA Inference Framework: Integrates sparse attention, model quantization, and speculative sampling to achieve efficient prefilling and decoding
-  - ArkInfer -- Cross-platform Deployment System: Supports efficient deployment across multiple backend environments, providing flexible cross-platform adaptation capabilities
-
-## Usage
-
-### Inference with [CPM.cu](https://github.com/OpenBMB/cpm.cu)
 
-We recommend using [CPM.cu](https://github.com/OpenBMB/cpm.cu) for the inference of MiniCPM4 and MiniCPM4.1. CPM.cu is a CUDA inference framework developed by OpenBMB, which integrates efficient sparse, speculative sampling, and quantization techniques, fully leveraging the efficiency advantages of MiniCPM4 and MiniCPM4.1.
+## Evaluation Results
 
-You can install CPM.cu by running the following command:
+### Performance Evaluation
+MiniCPM4.1 launches end-side versions with 8B parameter scale, both achieving best-in-class performance in their respective categories.
 
-```bash
-git clone https://github.com/OpenBMB/cpm.cu.git --recursive
-cd cpm.cu
-python3 setup.py install
-```
+![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/benchmark4.1.png?raw=true)
 
-MiniCPM4.1 natively supports context lengths of up to 65,536(64k) tokens. To reproduce the long-text acceleration effect in the paper, we recommend using the LongRoPE factors that have been validated. Change the `rope_scaling` field in the `config.json` file as the following to enable LongRoPE.
-```json
-{
-    ...,
-    "rope_scaling": {
-        "rope_type": "longrope", 
-        "long_factor": [0.9982316082870437, 1.033048153422584, 1.0749920956484724, 1.1255096879436193, 1.1863348602111476, 1.259543828902579, 1.3476188888731149, 1.4535223827776373, 1.5807816745852985, 1.7335856049489526, 1.9168922912975785, 2.1365471404135326, 2.3994084200118646, 2.713475511863602, 3.0880118452194134, 3.533650295140154, 4.062463396503134, 4.687974098908333, 5.425075306704039, 6.289818967956352, 7.29902962722721, 8.6357018163639, 10.210822723989212, 12.053807765671676, 14.193944598909404, 16.65780676784363, 19.463620727694074, 22.628311203524586, 26.150106147261315, 30.02526691405111, 34.23183327975347, 38.73811934094828, 43.502489489729555, 48.47627117965394, 53.61139491762471, 58.857366522037935, 64.16798299215064, 69.51359464319125, 74.86555458220285, 80.21497790341579, 85.55322183307433, 90.89611806932027, 96.26245306514224, 101.68269304046481, 107.18619510219668, 112.82253283014026, 118.63764063163615, 119.88866203644656, 120.9462882391725, 121.837565139014, 122.58663780572562, 123.2147719894291, 123.74049454862576, 124.17980424685767, 124.54641761955492, 124.85202548028222, 125.10654406389756, 125.31835105170659, 125.49450117164764, 125.64091910903052, 125.76256945356558, 125.86360463815589, 125.94749252260765, 126.01712561287873],
-        "short_factor": [0.9982316082870437, 1.033048153422584, 1.0749920956484724, 1.1255096879436193, 1.1863348602111476, 1.259543828902579, 1.3476188888731149, 1.4535223827776373, 1.5807816745852985, 1.7335856049489526, 1.9168922912975785, 2.1365471404135326, 2.3994084200118646, 2.713475511863602, 3.0880118452194134, 3.533650295140154, 4.062463396503134, 4.687974098908333, 5.425075306704039, 6.289818967956352, 7.29902962722721, 8.6357018163639, 10.210822723989212, 12.053807765671676, 14.193944598909404, 16.65780676784363, 19.463620727694074, 22.628311203524586, 26.150106147261315, 30.02526691405111, 34.23183327975347, 38.73811934094828, 43.502489489729555, 48.47627117965394, 53.61139491762471, 58.857366522037935, 64.16798299215064, 69.51359464319125, 74.86555458220285, 80.21497790341579, 85.55322183307433, 90.89611806932027, 96.26245306514224, 101.68269304046481, 107.18619510219668, 112.82253283014026, 118.63764063163615, 119.88866203644656, 120.9462882391725, 121.837565139014, 122.58663780572562, 123.2147719894291, 123.74049454862576, 124.17980424685767, 124.54641761955492, 124.85202548028222, 125.10654406389756, 125.31835105170659, 125.49450117164764, 125.64091910903052, 125.76256945356558, 125.86360463815589, 125.94749252260765, 126.01712561287873],
-        "original_max_position_embeddings": 65536
-    }
-}
-```
+### Efficiency Evaluation
+MiniCPM4.1 adopts sparse attention and speculative decoding to improve the inference efficiency. On RTX 4090, MiniCPM4.1 achieves 3x decoding speed improvement in reasoning.
 
-After modification, you can run the following command to reproduce the long-context acceleration effect (the script will automatically download the model weights from HuggingFace)
-```bash
-python3 tests/test_generate.py
-```
+![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/minicpm4.1_speed.png?raw=true)
 
-You can run the following command to infer with EAGLE3 speculative decoding algorithm.
+#### Examples
+<div align="center">
+  <a href="https://www.youtube.com/watch?v=VouXjLHKDUY"><img src="https://img.youtube.com/vi/VouXjLHKDUY/0.jpg", width=70%></a>
+</div>
 
-```bash
-python3 -m cpmcu.cli \
-    --model-path $BASE_MODEL_PATH \
-    --draft-model-path $EAGLE3_DRAFT_MODEL_PATH \
-    --prompt-text "Write an article about Artificial Intelligence." \
-    --use-eagle3 true
-```
 
-For more details about CPM.cu, please refer to [the repo CPM.cu](https://github.com/OpenBMB/cpm.cu).
 
-### Hybird Reasoning Mode
+## Usage
+MiniCPM 4.1 can be used with following frameworks: Huggingface Transformers, SGLang, vLLM, and CPM.cu. For the ultimate inference speed, we highly recommend CPM.cu.
 
-MiniCPM4.1 supports hybrid reasoning mode, which can be used in both deep reasoning mode and non-reasoning mode. To enable hybrid reasoning mode. User can set `enable_thinking=True` in `tokenizer.apply_chat_template` to enable hybrid reasoning mode, and set `enable_thinking=False` to enable non-reasoning mode. Similarly, user can directly add `/no_think` at the end of the query to enable non-reasoning mode. If not add any special token or add `/think` at the end of the query, the model will enable reasoning mode.
-
-```python
-# Enable reasoning mode
-prompt_text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True,
-    enable_thinking=True
-)
-# Enable non-reasoning mode
-prompt_text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True,
-    enable_thinking=False
-)
-```
 
 ### Inference with Transformers
 ```python
@@ -226,6 +170,8 @@ You can apply the LongRoPE factor modification by modifying the model files. Spe
 
 ### Inference with [SGLang](https://github.com/sgl-project/sglang)
 
+You can inference with SGLang using the standard mode and speculative decoding mode.
+
 #### Speculative Decoding
 
 For accelerated inference with speculative decoding, follow these steps:
@@ -246,7 +192,7 @@ The EAGLE3 adaptation PR has been submitted. For now, use our repository for ins
 ```bash
 git clone https://github.com/LDLINGLINGLING/sglang.git
 cd sglang
-pip install -e .
+pip install -e "python[all]"
 ```
 
 ##### 3. Launch SGLang Server with Speculative Decoding
@@ -337,6 +283,7 @@ print(response.choices[0].message.content)
 ```
 
 ### Inference with [vLLM](https://github.com/vllm-project/vllm)
+You can inference with vLLM using the standard mode and speculative decoding mode.
 
 #### Speculative Decoding
 
@@ -344,7 +291,7 @@ For accelerated inference with speculative decoding using vLLM, follow these ste
 
 ##### 1. Download MiniCPM4.1 Draft Model
 
-First, download the MiniCPM4.1 draft model:
+First, download the MiniCPM4.1 draft model and change the `architectures` in config.json as `LlamaForCausalLM`.
 
 ```bash
 cd /your_path
@@ -450,7 +397,7 @@ Also, you can start the inference server by running the following command:
 > **Note**: In vLLM's chat API, `add_special_tokens` is `False` by default. This means important special tokens—such as the beginning-of-sequence (BOS) token—will not be added automatically. To ensure the input prompt is correctly formatted for the model, you should explicitly set `extra_body={"add_special_tokens": True}`.
 
 ```bash
-vllm serve openbmb/MiniCPM4.1-8B 
+vllm serve openbmb/MiniCPM4.1-8B --trust-remote-code 
 ```
 
 Then you can use the chat interface by running the following code:
@@ -474,24 +421,69 @@ response = client.chat.completions.create(
 print(response.choices[0].message.content)
 ```
 
-## Evaluation Results
-On two typical end-side chips, Jetson AGX Orin and RTX 4090, MiniCPM4 demonstrates significantly faster processing speed compared to similar-size models in long text processing tasks. As text length increases, MiniCPM4's efficiency advantage becomes more pronounced. On the Jetson AGX Orin platform, compared to Qwen3-8B, MiniCPM4 achieves approximately 7x decoding speed improvement.
 
-![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/efficiency.png?raw=true)
+### Inference with [CPM.cu](https://github.com/OpenBMB/cpm.cu)
 
-MiniCPM4.1 achieves 3x decoding speed improvement in reasoning.
+We recommend using [CPM.cu](https://github.com/OpenBMB/cpm.cu) for the inference of MiniCPM4 and MiniCPM4.1. CPM.cu is a CUDA inference framework developed by OpenBMB, which integrates efficient sparse, speculative sampling, and quantization techniques, fully leveraging the efficiency advantages of MiniCPM4 and MiniCPM4.1.
 
-![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/minicpm4.1_speed.png?raw=true)
+You can install CPM.cu by running the following command:
 
-#### Comprehensive Evaluation
-MiniCPM4.1 launches end-side versions with 8B parameter scale, both achieving best-in-class performance in their respective categories.
+```bash
+git clone https://github.com/OpenBMB/cpm.cu.git --recursive
+cd cpm.cu
+python3 setup.py install
+```
 
-![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/benchmark4.1.png?raw=true)
+MiniCPM4.1 natively supports context lengths of up to 65,536(64k) tokens. To reproduce the long-text acceleration effect in the paper, we recommend using the LongRoPE factors that have been validated. Change the `rope_scaling` field in the `config.json` file as the following to enable LongRoPE.
+```json
+{
+    ...,
+    "rope_scaling": {
+        "rope_type": "longrope", 
+        "long_factor": [0.9982316082870437, 1.033048153422584, 1.0749920956484724, 1.1255096879436193, 1.1863348602111476, 1.259543828902579, 1.3476188888731149, 1.4535223827776373, 1.5807816745852985, 1.7335856049489526, 1.9168922912975785, 2.1365471404135326, 2.3994084200118646, 2.713475511863602, 3.0880118452194134, 3.533650295140154, 4.062463396503134, 4.687974098908333, 5.425075306704039, 6.289818967956352, 7.29902962722721, 8.6357018163639, 10.210822723989212, 12.053807765671676, 14.193944598909404, 16.65780676784363, 19.463620727694074, 22.628311203524586, 26.150106147261315, 30.02526691405111, 34.23183327975347, 38.73811934094828, 43.502489489729555, 48.47627117965394, 53.61139491762471, 58.857366522037935, 64.16798299215064, 69.51359464319125, 74.86555458220285, 80.21497790341579, 85.55322183307433, 90.89611806932027, 96.26245306514224, 101.68269304046481, 107.18619510219668, 112.82253283014026, 118.63764063163615, 119.88866203644656, 120.9462882391725, 121.837565139014, 122.58663780572562, 123.2147719894291, 123.74049454862576, 124.17980424685767, 124.54641761955492, 124.85202548028222, 125.10654406389756, 125.31835105170659, 125.49450117164764, 125.64091910903052, 125.76256945356558, 125.86360463815589, 125.94749252260765, 126.01712561287873],
+        "short_factor": [0.9982316082870437, 1.033048153422584, 1.0749920956484724, 1.1255096879436193, 1.1863348602111476, 1.259543828902579, 1.3476188888731149, 1.4535223827776373, 1.5807816745852985, 1.7335856049489526, 1.9168922912975785, 2.1365471404135326, 2.3994084200118646, 2.713475511863602, 3.0880118452194134, 3.533650295140154, 4.062463396503134, 4.687974098908333, 5.425075306704039, 6.289818967956352, 7.29902962722721, 8.6357018163639, 10.210822723989212, 12.053807765671676, 14.193944598909404, 16.65780676784363, 19.463620727694074, 22.628311203524586, 26.150106147261315, 30.02526691405111, 34.23183327975347, 38.73811934094828, 43.502489489729555, 48.47627117965394, 53.61139491762471, 58.857366522037935, 64.16798299215064, 69.51359464319125, 74.86555458220285, 80.21497790341579, 85.55322183307433, 90.89611806932027, 96.26245306514224, 101.68269304046481, 107.18619510219668, 112.82253283014026, 118.63764063163615, 119.88866203644656, 120.9462882391725, 121.837565139014, 122.58663780572562, 123.2147719894291, 123.74049454862576, 124.17980424685767, 124.54641761955492, 124.85202548028222, 125.10654406389756, 125.31835105170659, 125.49450117164764, 125.64091910903052, 125.76256945356558, 125.86360463815589, 125.94749252260765, 126.01712561287873],
+        "original_max_position_embeddings": 65536
+    }
+}
+```
 
-#### Long Text Evaluation
-MiniCPM4 is pre-trained on 32K long texts and achieves length extension through YaRN technology. In the 128K long text needle-in-a-haystack task, MiniCPM4 demonstrates outstanding performance.
+After modification, you can run the following command to reproduce the long-context acceleration effect (the script will automatically download the model weights from HuggingFace)
+```bash
+python3 tests/test_generate.py
+```
 
-![long-niah](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/128k-niah.png?raw=true)
+You can run the following command to infer with EAGLE3 speculative decoding algorithm.
+
+```bash
+python3 -m cpmcu.cli \
+    --model-path $BASE_MODEL_PATH \
+    --draft-model-path $EAGLE3_DRAFT_MODEL_PATH \
+    --prompt-text "Write an article about Artificial Intelligence." \
+    --use-eagle3 true
+```
+
+For more details about CPM.cu, please refer to [the repo CPM.cu](https://github.com/OpenBMB/cpm.cu).
+
+### Hybird Reasoning Mode
+
+MiniCPM4.1 supports hybrid reasoning mode, which can be used in both deep reasoning mode and non-reasoning mode. To enable hybrid reasoning mode. User can set `enable_thinking=True` in `tokenizer.apply_chat_template` to enable hybrid reasoning mode, and set `enable_thinking=False` to enable non-reasoning mode. Similarly, user can directly add `/no_think` at the end of the query to enable non-reasoning mode. If not add any special token or add `/think` at the end of the query, the model will enable reasoning mode.
+
+```python
+# Enable reasoning mode
+prompt_text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True
+)
+# Enable non-reasoning mode
+prompt_text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=False
+)
+```
 
 ## Statement
 - As a language model, MiniCPM generates content by learning from a vast amount of text.