Update model card: Add pipeline tag

This PR improves the model card by:

- Adding the `pipeline_tag: text-generation` to correctly categorize the model and enable its discoverability on the Hugging Face Hub. This tag is well-supported by the paper's abstract and model description.
- The `library_name` remains `CALM`. Although the `config.json` references a `transformers_version`, the model architecture (`Autoencoder`) and common usage patterns (often requiring `trust_remote_code=True`) suggest that it may not be fully natively integrated with the standard `transformers` auto-loading mechanism for the automated "how to use" widget. Retaining `CALM` avoids a potentially broken default code snippet.
- No sample usage section is added, as the provided GitHub README content does not contain an explicit Python code snippet for inference, following the strict guidelines.

Please review and merge if these changes are appropriate.

README.md

@@ -1,15 +1,16 @@
 ---
-license: mit
 datasets:
 - monology/pile-uncopyrighted
 language:
 - en
 library_name: CALM
+license: mit
+metrics:
+- BrierLM
 tags:
 - large language models
 - language modeling
-metrics:
-- BrierLM
+pipeline_tag: text-generation
 ---
 
 # Continuous Autoregressive Language Models
@@ -25,19 +26,19 @@ 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:
+*   🚀 **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.
+  *   **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
 
@@ -45,4 +46,4 @@ See our [GitHub README](https://github.com/shaochenze/calm), where we provide sc
 
 ## 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`.