Improve model card for Switch Generation model with paper, GitHub links, usage, and metadata

This PR significantly improves the model card for the "Switch Generation" model.

Key updates include:
* **Comprehensive Description**: The boilerplate text has been replaced with a detailed summary derived from the paper's abstract, explaining the novel "Switch Generation" concept.
* **Metadata Enrichment**:
* The `pipeline_tag: text-generation` has been added for better discoverability on the Hugging Face Hub.
* Relevant tags such as `llama`, `model-collaboration`, and `instruction-following` have been included.
* The `base_model` has been explicitly listed (`allenai/Llama-3.1-Tulu-3-8B`).
* The license is set to `other` as no explicit license was found in the source materials.
* **Linked Resources**: Direct links to the academic paper ([Don't Throw Away Your Pretrained Model](https://huggingface.co/papers/2510.09913)) and the associated GitHub repository (`https://github.com/BunsenFeng/switch_generation`) have been added.
* **Getting Started Guide**: A "How to Get Started" section, including code snippets for environment setup and inference, has been extracted directly from the GitHub README.

These changes make the model card much more informative and user-friendly for researchers and practitioners.

README.md

@@ -1,127 +1,130 @@
 ---
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
+license: other
+tags:
+  - llama
+  - model-collaboration
+  - instruction-following
+base_model: allenai/Llama-3.1-Tulu-3-8B
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Model Card for Switch Generation
 
+This model implements **Switch Generation**, a novel approach presented in the paper [Don't Throw Away Your Pretrained Model](https://huggingface.co/papers/2510.09913). Switch Generation aims to make the best of both worlds by enabling pretrained and aligned model versions to "speak" in turns within a response sequence. This method addresses the tradeoffs of alignment training by leveraging model collaboration, where a "switcher LM" dynamically guides different model checkpoints to generate segments where their strengths are most needed. Extensive experiments show that Switch Generation consistently outperforms individual models and baselines, discovering compositional skills and reusing by-products from expensive training pipelines.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+Switch Generation is a model collaboration framework designed to overcome the limitations of alignment training, which can lead to losses in skills like creativity and calibration, where unaligned base models often excel. The core idea is to train a "switcher LM" that learns to choose between different models (e.g., a pretrained base model and an aligned version) to generate the next segment of text. This dynamic switching allows the system to harness the unique strengths of each participating model, leading to improved performance across tasks requiring diverse skills such as reasoning, instruction following, creativity, and calibration. It generalizes to unseen models and tasks by effectively repurposing existing model assets.
 
-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]
+-   **Model type:** Switcher Language Model (LoRA adapter for Causal LM orchestration)
+-   **Language(s) (NLP):** English
+-   **License:** other
+-   **Finetuned from model:** [allenai/Llama-3.1-Tulu-3-8B](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B)
 
-- **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
 
-### Model Sources [optional]
+-   **Repository:** https://github.com/BunsenFeng/switch_generation
+-   **Paper:** [Don't Throw Away Your Pretrained Model](https://huggingface.co/papers/2510.09913)
 
-<!-- Provide the basic links for the model. -->
+## Uses
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+### Direct Use
 
-## Uses
+The Switch Generation framework is intended for text generation tasks where combining the strengths of different language models (e.g., aligned for instruction following and unaligned for creativity) can lead to superior and more balanced responses. It is designed to orchestrate the generation process by dynamically selecting the most suitable underlying model for each segment.
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Out-of-Scope Use
 
-### Direct Use
+This model is not intended for standalone direct text generation without the orchestrated collaboration of multiple underlying language models. It functions as a "switcher" or controller within a larger generation system. As with any language model, users should be aware of potential biases and limitations in generated content.
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+## How to Get Started with the Model
 
-[More Information Needed]
+Use the code below to get started with the model.
 
-### Downstream Use [optional]
+### Quick Start
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+#### Initialization
 
-[More Information Needed]
+Create a conda environment for Switch Generation
+```
+conda env create -f switch.yml
+conda activate switch_generation
+```
 
-### Out-of-Scope Use
+Log into huggingface (for model access).
+```
+huggingface-cli login
+```
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+#### Execute your first Switch Generation inference
 
-[More Information Needed]
+```
+bash main.sh
+```
 
-## Bias, Risks, and Limitations
+`main.sh` by default contains:
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+```
+python main_generate.py \
+        --input data/input_sample.jsonl \
+        --gpu_ids 0,1,2,3 \
+        --overide_selector_path bunsenfeng/PFA_switcher_1 \
+        --total_max_length 256
+```
 
-[More Information Needed]
+`--input`: a JSONL file of inputs, look at `data/input_sample.jsonl` for an example of how to prepare your custom inputs. Output will come out at the same directory `data/input_sample_switch_generation.jsonl`.
 
-### Recommendations
+`--gpu_ids`: a string of numbers separated by comma, 4 GPUs needed (one for P, F, A, and switcher each).
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+`--overide_selector_path`: path to the switcher LM on Huggingface. We provide `bunsenfeng/PFA_switcher_1`, `bunsenfeng/PFA_switcher_2` with different task and training exposure, you can also just try the aligned model itself `allenai/Llama-3.1-Tulu-3-8B` or any model that could follow instructions.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+`--total_max_length`: essentially `max_new_tokens`.
 
-## How to Get Started with the Model
+#### Other Settings
 
-Use the code below to get started with the model.
+Your own data: format it like `data/input_sample.jsonl`.
 
-[More Information Needed]
+Your own candidate models: change in lines 46-48 in `main_generate.py`. Make sure `--gpu_ids` provides (n+1) GPU ids where n is the amount of candidate models. Can be other than 3 models. Another recommended set: `["Qwen/Qwen2.5-7B", "bunsenfeng/yuru_qw_oasst1", "Qwen/Qwen2.5-7B-Instruct"]`, where the middle is an SFT model we made in [here](https://arxiv.org/abs/2506.04721).
 
 ## 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. -->
+The switcher LM is trained by learning from outcomes of choosing different models to generate the next segment across diverse queries and contexts. At inference time, the switcher LM guides different model checkpoints to dynamically generate the next segment where their strengths are most needed.
 
 #### 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 -->
+-   **Training regime:** [More Information Needed]
 
 #### 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
@@ -130,25 +133,19 @@ Use the code below to get started with the model.
 
 #### 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]
+-   **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]
 
@@ -168,9 +165,9 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 [More Information Needed]
 
-## Citation [optional]
+## Citation
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+If Switch Generation is helpful to you:
 
 **BibTeX:**
 
@@ -182,8 +179,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## 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]