TokenSwift
/

TokenSwift-Qwen2.5-14B

@@ -1,199 +1,80 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## 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]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 ## 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]
-### 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]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
 ## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
 ### 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.
 ## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
 ## 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]
 ### 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]
 ## 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]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+pipeline_tag: text-generation
+license: apache-2.0
+tags: [long-sequence-generation, lossless-acceleration]
 ---
+# Model Card for TokenSwift Models
+TokenSwift is a novel framework designed to substantially accelerate the generation process of ultra-long sequences (up to 100K tokens) while maintaining the target model's inherent quality. This model achieves over 3x speedup across various models and architectures, saving hours of time for ultra-long sequence generation. It addresses three major challenges: frequent model reloading, dynamic key-value (KV) management, and repetitive generation.
+[**Paper:** From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens](https://hf.co/papers/2502.18890)
+[**Code:** bigai-nlco/TokenSwift](https://github.com/bigai-nlco/TokenSwift)
+[**Website:** TokenSwift](https://bigai-nlco.github.io/TokenSwift/)
+## Model Details
+This model is a framework for accelerating the generation of ultra-long sequences (up to 100K tokens) using large language models (LLMs). It is compatible with the Hugging Face `transformers` library. It achieves lossless acceleration by addressing inefficiencies in traditional speculative decoding methods.
+### Model Sources
+- **Repository:** [HuggingFace](https://huggingface.co/TokenSwift)
 ## Uses
 ### Direct Use
+TokenSwift can be used to significantly speed up the generation of long sequences with various LLMs. The framework is designed to be easily integrated with existing Hugging Face models.
 ## Bias, Risks, and Limitations
+As an acceleration framework, TokenSwift inherits the biases and limitations of the underlying LLM it's used with. It does not introduce new biases but may amplify existing ones depending on the base model. Potential risks include the possibility of generating inaccurate or harmful content if the base LLM is prone to such outputs.
 ### Recommendations
+Users should carefully select the base LLM and be mindful of its inherent biases and limitations. The output of the model should be critically evaluated.
 ## How to Get Started with the Model
+See the [Getting Started](#getting-started) section in the main README for detailed instructions on downloading models and performing inference.
 ## Training Details
 ### Training Data
+The models were trained on a subset of the [PG-19](https://huggingface.co/datasets/deepmind/pg19) dataset, filtering out sequences longer than 8K tokens. Processed training datasets are also available on HuggingFace.
 ### Training Procedure
+See the [Training Guide (Optional)](#training-guide-optional) section in the main README.
 ## Evaluation
+The evaluation protocol involved benchmarking the speed of TokenSwift across multiple LLMs and sequence lengths (20K, 40K, 60K, 80K, 100K tokens). The key metric was speedup compared to vanilla decoding, demonstrating a consistent 3x improvement.
 ### Results
+The results demonstrate a significant speedup in ultra-long sequence generation without loss of quality.
+## Citation
 **BibTeX:**
+```bibtex
+@misc{tokenswift,
+      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},
+}
+```