Update model card: Add `text-generation` pipeline tag, `transformers` library, and sample usage

README.md

@@ -1,15 +1,16 @@
 ---
-license: mit
 datasets:
 - monology/pile-uncopyrighted
 language:
 - en
-library_name: CALM
+library_name: transformers
+license: mit
+metrics:
+- BrierLM
 tags:
 - large language models
 - language modeling
-metrics:
-- BrierLM
+pipeline_tag: text-generation
 ---
 
 # Continuous Autoregressive Language Models
@@ -17,7 +18,7 @@ metrics:
 [![Paper](https://img.shields.io/badge/Paper_📃-green)](https://arxiv.org/abs/2510.27688)
 [![GitHub](https://img.shields.io/badge/GitHub_🧑‍💻-blue)](https://github.com/shaochenze/calm)
 [![HuggingFace](https://img.shields.io/badge/HuggingFace_🤗-orange)](https://huggingface.co/collections/cccczshao/calm)
-[![Blog](https://img.shields.io/badge/Blog_✍️-yellowgreen)](https://shaochenze.github.io/blog/2025/CALM/)
+[![Project Page](https://img.shields.io/badge/Project_Page_✍️-yellowgreen)](https://shaochenze.github.io/blog/2025/CALM/)
 
 ## Model Description
 
@@ -25,24 +26,43 @@ Modern Large Language Models (LLMs) are constrained by a fundamental bottleneck:
 
 This is achieved through a two-stage process:
 
-1. **A high-fidelity autoencoder** learns to compress K tokens into a single vector and reconstruct them with near-perfect accuracy.
-2. **A continuous-domain language model** then performs autoregressive prediction in this vector space.
+1.  **A high-fidelity autoencoder** learns to compress K tokens into a single vector and reconstruct them with near-perfect accuracy.
+2.  **A continuous-domain language model** then performs autoregressive prediction in this vector space.
 
 ### Key Features
 
-* 🚀 **Ultra-Efficient by Design:** Dramatically improves training and inference efficiency by reducing the number of autoregressive steps by a factor of K.
-* 💡 **A New Scaling Axis:** Introduces a new scaling dimension for LLMs—semantic bandwidth (K). Instead of just scaling parameters and data, you can now scale the amount of information processed in a single step.
-* 🛠️ **A Comprehensive Likelihood-Free Toolkit:** Operating in a continuous domain requires new tools. This repository provides the full suite of algorithms that make CALM possible:
-  
-  * **A Robust Autoencoder** to learn high-fidelity continuous representations of token chunks.
-  * **Energy-Based Training**, a principled and likelihood-free method for generative modeling.
-  * **BrierLM**, a new metric for calibrated, likelihood-free evaluation of language models.
-  * **Temperature Sampling** for controlled, high-quality text generation using only a black-box sampler.
+*   🚀 **Ultra-Efficient by Design:** Dramatically improves training and inference efficiency by reducing the number of autoregressive steps by a factor of K.
+*   💡 **A New Scaling Axis:** Introduces a new scaling dimension for LLMs—**semantic bandwidth (K)**. Instead of just scaling parameters and data, you can now scale the amount of information processed in a single step.
+*   🛠️ **A Comprehensive Likelihood-Free Toolkit:** Operating in a continuous domain requires new tools. This repository provides the full suite of algorithms that make CALM possible:
+    *   **A Robust Autoencoder** to learn high-fidelity continuous representations of token chunks.
+    *   **Energy-Based Training**, a principled and likelihood-free method for generative modeling.
+    *   **BrierLM**, a new metric for calibrated, likelihood-free evaluation of language models.
+    *   **Temperature Sampling** for controlled, high-quality text generation using only a black-box sampler.
 
 ## How to use
 
-See our [GitHub README](https://github.com/shaochenze/calm), where we provide scripts for training and evaluation.
+We provide scripts for training and evaluation in our [GitHub README](https://github.com/shaochenze/calm).
+
+### Sample Usage (Text Generation)
+
+You can explore the core implementation of **CALM** in the GitHub repository. We've made it easy to use CALM by including our custom code in the 🤗[Hugging Face model zoo](https://huggingface.co/collections/cccczshao/calm). Simply set `trust_remote_code=True` when loading the models through the Transformers library.
+
+```python
+from transformers import pipeline, AutoTokenizer
+import torch
+
+model_name = "cccczshao/CALM-M" # Example model from the collection
+pipe = pipeline(
+    "text-generation",
+    model_name,
+    tokenizer=AutoTokenizer.from_pretrained(model_name),
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+print(pipe("The key to life is", max_new_tokens=20, do_sample=True)[0]["generated_text"])
+```
 
 ## Contact
 
-If you have any questions, feel free to submit an issue or contact `chenzeshao@tencent.com`.
+If you have any questions, feel free to submit an issue or contact `chenzeshao@tencent.com`.