Populate Model Card with Details for TokenSwift

README.md

@@ -1,199 +1,100 @@
 ---
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
+license: mit # Assuming MIT license based on common open-source practices. Please verify.
+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 framework that achieves lossless acceleration for ultra-long sequence generation (up to 100K tokens), reducing computation time from hours to minutes. It works with most HuggingFace models and offers linear time complexity for long sequences.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+TokenSwift is not a model itself, but a framework for accelerating the generation of long sequences (up to 100K tokens) in large language models. It achieves this by using a tree-based approach to constructing candidate tokens and verifying them against the target model's output. This allows for significant speedups (up to 3x) without sacrificing the quality of the generated text. The framework is compatible with various HuggingFace models.
 
-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]
+- **Developed by:** BigAI-NLCO
+- **Model type:** Framework for accelerating LLM text generation
+- **Language(s) (NLP):** Multilingual (depending on the underlying LLM)
+- **License:** MIT
+- **Finetuned from model [optional]:** N/A (framework, not a fine-tuned model)
 
 ### Model Sources [optional]
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** https://github.com/bigai-nlco/TokenSwift
+- **Paper [optional]:** [From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens](https://arxiv.org/abs/2502.18890)
+- **Demo [optional]:** (Link to demo if available)
 
 ## 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 to accelerate the text generation process of existing LLMs. It is designed to be a plug-and-play framework that can improve the efficiency of various models.
 
 ### Downstream Use [optional]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+TokenSwift can be integrated into any application that utilizes LLMs for text generation, particularly those requiring the generation of very long sequences. This includes applications such as story generation, document summarization, and code generation.
 
 ### 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 intended for tasks that do not require long-sequence generation or for models with architectures incompatible with its design.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+TokenSwift itself does not introduce new biases or risks. However, it inherits the biases and limitations of the underlying LLM it accelerates. The accuracy and safety of the generated text will depend entirely on the base LLM used.
 
 ### 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 carefully consider the biases and limitations of the underlying LLM when using TokenSwift. The framework only improves efficiency; it doesn't address inherent biases or safety concerns.
 
 ## 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 README for instructions.
 
 ## 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. -->
-
-[More Information Needed]
+The training data consists of long sequences from the PG-19 dataset, with sequences longer than 8K tokens filtered out based on the tokenizer used.
 
 ### 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 (Option)](#training-guide-option) section of the README.
 
 ## 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]
+The evaluation used benchmarks with varying sequence lengths (20K, 40K, 60K, 80K, 100K tokens). Metrics included speedup and quality (matching original model's output).
 
 ### Results
 
-[More Information Needed]
+See the [Introduction](#introduction) section for results visualizations.
 
 #### 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]
+TokenSwift achieves significant speedups (up to 3x) compared to baseline methods, without compromising the quality of the generated text.
 
 ## 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]
+```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}, 
+}
+```
 
 **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]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+Wu, T., Shen, J., Jia, Z., Wang, Y., & Zheng, Z. (2025). *From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens*. arXiv preprint arXiv:2502.18890.