Update README.md

Adding model card

README.md

@@ -1,199 +1,207 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- biology
+- protein-language-model
+- protein-generation
+- causal-lm
+- mixture-of-experts
+- transformers
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
+# Model Card for ProtGPT3-112M
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+ProtGPT3-112M is a single-sequence autoregressive protein language model for protein sequence generation. It is part of the ProtGPT3 family, an open-source suite of promptable and aligned protein language models ranging from 112M to 10B parameters. ProtGPT3 models use a causal Mixtral-style Mixture-of-Experts architecture and are trained for causal language modeling on protein sequences.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+The single-sequence ProtGPT3 models can generate proteins in either N-to-C or C-to-N direction using special directional tokens. The model is intended for unconditional or prefix-conditioned protein sequence generation and can be used as a base model for downstream protein design workflows.
 
-- **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:** Anonymous authors
+- **Model type:** Autoregressive protein language model; causal decoder-only Mixture-of-Experts model
+- **Language(s):** Protein sequences / amino-acid sequences
+- **License:** More Information Needed
+- **Finetuned from model:** Not applicable / pretrained from scratch
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** https://huggingface.co/protgpt3
+- **Paper:** ProtGPT3: an Open-source family of Promptable and Aligned Protein Language Models
+- **Code:** https://anonymous.4open.science/r/protGPT3-2053/README.md
 
 ## 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]
+ProtGPT3-112M can be used for autoregressive generation of protein sequences. Users can generate sequences unconditionally or condition generation on an amino-acid prefix.
 
-### 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 model may be fine-tuned or incorporated into protein design workflows, including family-specific generation, protein variant generation, and computational screening pipelines.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+The model should not be used as the sole basis for experimental, clinical, environmental, or safety-critical decisions. Generated proteins require downstream computational and experimental validation. The model is not guaranteed to generate functional, soluble, safe, or synthesizable proteins.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+ProtGPT3-112M learns from public protein sequence datasets and may reproduce biases present in those datasets. Generated sequences may be low-complexity, nonfunctional, unstable, insoluble, or biologically implausible. Protein generation models may also present dual-use risks if used irresponsibly.
 
 ### 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 apply appropriate computational filters, expert review, and experimental validation before using generated sequences. Users should also consider responsible-use practices for generative protein design.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+Install dependencies:
 
-[More Information Needed]
+```bash
+pip install transformers accelerate torch
+```
 
-## Training Details
+Load the model and tokenizer:
 
-### 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
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+model_id = "protgpt3/ProtGPT3-112M"  # Replace with the final checkpoint name
 
-#### Preprocessing [optional]
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
 
-[More Information Needed]
+model.eval()
+```
 
+Generate a protein sequence:
 
-#### Training Hyperparameters
+```python
+import torch
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+prompt = ""  # Optionally provide an amino-acid prefix or model-specific direction token
 
-#### Speeds, Sizes, Times [optional]
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+with torch.no_grad():
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.8,
+        top_p=0.9,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.eos_token_id,
+    )
 
-[More Information Needed]
+sequence = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(sequence)
+```
 
-## Evaluation
+Generate from an amino-acid prefix:
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+```python
+prefix = "MKT"
 
-### Testing Data, Factors & Metrics
-
-#### Testing Data
+inputs = tokenizer(prefix, return_tensors="pt").to(model.device)
 
-<!-- This should link to a Dataset Card if possible. -->
+with torch.no_grad():
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        do_sample=True,
+        temperature=0.8,
+        top_p=0.9,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.eos_token_id,
+    )
 
-[More Information Needed]
+sequence = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(sequence)
+```
 
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
+## Training Details
 
-#### Metrics
+### Training Data
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+ProtGPT3-112M was trained on publicly available protein sequence data from UniRef90 and the GigaRef subset of the Dayhoff Atlas. The 112M-parameter model used approximately 15M UniRef90 sequences and 28M GigaRef sequences, corresponding to approximately 9.8B training tokens.
 
-[More Information Needed]
+### Training Procedure
 
-### Results
+#### Preprocessing
 
-[More Information Needed]
+Protein sequences were sampled from UniRef90 and GigaRef. During training, each sequence was assigned a generation direction, either N-to-C or C-to-N, with a special token prepended to indicate the direction.
 
-#### Summary
+#### Training Hyperparameters
 
+- **Training regime:** bfloat16
+- **Architecture:** Mixtral-style sparse Mixture-of-Experts causal decoder
+- **Maximum sequence length:** 1024
+- **Optimizer:** AdamW
+- **Learning rate:** 5e-4
+- **Weight decay:** 0.1
+- **Gradient clipping:** 1.0
+- **Batch size:** 500
+- **Number of training GPUs:** 4
 
+## Evaluation
 
-## Model Examination [optional]
+### Testing Data, Factors & Metrics
 
-<!-- Relevant interpretability work for the model goes here -->
+#### Testing Data
 
-[More Information Needed]
+The model was evaluated on held-out protein sequences with at most 50% sequence identity to the training set. It was also benchmarked on ProteinGym.
 
-## Environmental Impact
+#### Metrics
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+Evaluation included validation perplexity, sequence diversity, predicted pLDDT, proportion of terminating sequences, proportion of low-complexity sequences, and ProteinGym Spearman correlation.
 
-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).
+### Results
 
-- **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]
+Larger ProtGPT3 single-sequence models showed improved perplexity, sequence quality, and diversity. ProtGPT3-112M serves as the smallest single-sequence model in the family and provides a computationally accessible checkpoint for protein generation.
 
-## Technical Specifications [optional]
+## Technical Specifications
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+ProtGPT3-112M is a decoder-only causal language model using a Mixtral-style sparse Mixture-of-Experts architecture. It was trained with a causal language modeling objective on protein sequences.
 
 ### Compute Infrastructure
 
-[More Information Needed]
-
 #### Hardware
 
-[More Information Needed]
+NVIDIA H100 GPUs.
 
 #### Software
 
-[More Information Needed]
-
-## Citation [optional]
+Training used FlashAttention-2, online mini-batch packing, Liger Kernel, and DeepSpeed.
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+## Citation
 
 **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]
+```bibtex
+@article{protgpt3,
+  title={ProtGPT3: an Open-source family of Promptable and Aligned Protein Language Models},
+  author={Anonymous Authors},
+  year={2026}
+}
+```
 
-## More Information [optional]
+## More Information
 
-[More Information Needed]
+All models and code are released through the Hugging Face ecosystem and accompanying code repository.
 
-## Model Card Authors [optional]
+## Model Card Authors
 
-[More Information Needed]
+Anonymous authors
 
 ## Model Card Contact
 
-[More Information Needed]
+Anonymous authors