Add model description and link to paper (#5)

- Add model description and link to paper (f9c341a8fbe4c21c893d7e20421ba25e884ba8c9)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,11 +1,14 @@
 ---
-license: apache-2.0
 language:
 - zh
 - en
-pipeline_tag: text-generation
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 ---
+
+MiniCPM4-8B is a highly efficient large language model (LLM) designed explicitly for end-side devices. It achieves this efficiency through systematic innovation in model architecture, training data, training algorithms, and inference systems. The details can be found in [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://huggingface.co/papers/2506.07900).
+
 <div align="center">
 <img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img> 
 </div>
@@ -80,13 +83,6 @@ MiniCPM4 natively supports context lengths of up to 32,768 tokens. To reproduce
 }
 ```
 
-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
-```
-
-For more details about CPM.cu, please refer to [the repo CPM.cu](https://github.com/OpenBMB/cpm.cu).
-
 ### Inference with Transformers
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -199,112 +195,4 @@ Then you can use the chat interface by running the following command:
 ```python
 import openai
 
-client = openai.Client(base_url=f"http://localhost:30000/v1", api_key="None")
-
-response = client.chat.completions.create(
-    model="openbmb/MiniCPM4-8B",
-    messages=[
-        {"role": "user", "content": "Write an article about Artificial Intelligence."},
-    ],
-    temperature=0.7,
-    max_tokens=1024,
-)
-
-print(response.choices[0].message.content)
-```
-
-### Inference with [vLLM](https://github.com/vllm-project/vllm)
-For now, you need to install the latest version of vLLM.
-```
-pip install -U vllm \
-    --pre \
-    --extra-index-url https://wheels.vllm.ai/nightly
-```
-
-Then you can inference MiniCPM4-8B with vLLM:
-```python
-from transformers import AutoTokenizer
-from vllm import LLM, SamplingParams
-
-model_name = "openbmb/MiniCPM4-8B"
-prompt = [{"role": "user", "content": "Please recommend 5 tourist attractions in Beijing. "}]
-
-tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-input_text = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
-
-llm = LLM(
-    model=model_name,
-    trust_remote_code=True,
-    max_num_batched_tokens=32768, 
-    dtype="bfloat16", 
-    gpu_memory_utilization=0.8, 
-)
-sampling_params = SamplingParams(top_p=0.7, temperature=0.7, max_tokens=1024, repetition_penalty=1.02)
-
-outputs = llm.generate(prompts=input_text, sampling_params=sampling_params)
-
-print(outputs[0].outputs[0].text)
-```
-
-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/MiniCPM4-8B 
-```
-
-Then you can use the chat interface by running the following code:
-
-```python
-import openai
-
-client = openai.Client(base_url="http://localhost:8000/v1", api_key="EMPTY")
-
-response = client.chat.completions.create(
-    model="openbmb/MiniCPM4-8B",
-    messages=[
-        {"role": "user", "content": "Write an article about Artificial Intelligence."},
-    ],
-    temperature=0.7,
-    max_tokens=1024,
-    extra_body=dict(add_special_tokens=True),  # Ensures special tokens are added for chat template
-    
-)
-
-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)
-
-#### Comprehensive Evaluation
-MiniCPM4 launches end-side versions with 8B and 0.5B parameter scales, both achieving best-in-class performance in their respective categories.
-
-![benchmark](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/benchmark.png?raw=true)
-
-#### 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.
-
-![long-niah](https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm4/128k-niah.png?raw=true)
-
-## Statement
-- As a language model, MiniCPM generates content by learning from a vast amount of text. 
-- However, it does not possess the ability to comprehend or express personal opinions or value judgments. 
-- Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers. 
-- Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own.
-
-## LICENSE
-- This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License. 
-
-## Citation
-- Please cite our [paper](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf) if you find our work valuable.
-
-```bibtex
-@article{minicpm4,
-  title={{MiniCPM4}: Ultra-Efficient LLMs on End Devices},
-  author={MiniCPM Team},
-  year={2025}
-}
-```
+client =