Add model card for TokenSwift

README.md

@@ -1,199 +1,89 @@
 ---
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
+license: apache-2.0 # Please verify license
+tags: [long-sequence-generation, lossless-acceleration]
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Model Card for TokenSwift
 
+**TokenSwift** is a novel framework that achieves **lossless acceleration** for ultra-long sequence generation (up to 100K tokens), reducing computation time from hours to minutes.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+TokenSwift is a framework designed to accelerate the generation of long sequences in large language models without sacrificing the quality of the output. It works as a plug-and-play solution with most Hugging Face models, providing a 3x speedup.
 
-### Model Sources [optional]
+- **Developed by:** BigAI-NLCO
+- **Model type:** Model Adapter Framework
+- **Language(s) (NLP):** Multiple, depending on the underlying LLM
+- **License:** Apache-2.0 # Please verify license
+- **Finetuned from model [optional]:**  Various Hugging Face LLMs (see Inference section)
 
-<!-- Provide the basic links for the model. -->
+### Model Sources
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [https://github.com/bigai-nlco/TokenSwift](https://github.com/bigai-nlco/TokenSwift)
+- **Paper:** [https://arxiv.org/abs/2502.18890](https://arxiv.org/abs/2502.18890)
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
+TokenSwift is used as a framework to accelerate the inference of existing Hugging Face LLMs, particularly for long sequence generation.
 
-### Downstream Use [optional]
+### Downstream Use
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+The accelerated LLMs can be used for any downstream task supported by the underlying base model.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+TokenSwift is not designed for tasks that do not involve text generation or where short sequence lengths are sufficient.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+TokenSwift inherits the biases and limitations of the underlying language model it is used with.
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Users should be aware of the potential biases and limitations of the base language model used with TokenSwift.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+See the [Inference](#inference) section of the GitHub README for usage instructions. Pre-trained TokenSwift adapters are available on the Hugging Face Hub.
 
 ## Training Details
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+The training data is derived from the PG-19 dataset. Data longer than 8K tokens are filtered out. Processed training datasets are available at:
 
-[More Information Needed]
+-   llama2-pg19: [https://huggingface.co/datasets/TokenSwift/llama2\_pg19\_train\_data](https://huggingface.co/datasets/TokenSwift/llama2_pg19_train_data)
+-   llama3.1-pg19: [https://huggingface.co/datasets/TokenSwift/llama3.1\_pg19\_train\_data](https://huggingface.co/datasets/TokenSwift/llama3.1_pg19_train_data)
+-   qwen2.5-pg19: [https://huggingface.co/datasets/TokenSwift/qwen2.5\_pg19\_train\_data](https://huggingface.co/datasets/TokenSwift/qwen2.5_pg19_train_data)
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
+See the [Training Guide](#training-guide-option) section of the GitHub README for details.
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
+See the GitHub README for benchmark results.
 
-## Model Card Authors [optional]
+## Citation
 
-[More Information Needed]
+```bibtex
+@misc{wu2025hoursminuteslosslessacceleration,
+      title={From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens},
+      author={Tong Wu and Junzhe Shen and Zixia Jia and Yuxuan Wang and Zilong Zheng},
+      year={2025},
+      eprint={2502.18890},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2502.18890},
+}
+```
 
-## Model Card Contact
+## Acknowledgment
 
-[More Information Needed]
+This codebase is influenced by remarkable projects from the LLM community, including [Medusa](https://github.com/FasterDecoding/Medusa/tree/main) and [TriForce](https://github.com/Infini-AI-Lab/TriForce).