| --- |
| library_name: transformers |
| base_model: JuIm/ProGemma2 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: ProGemma2 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # ProteinLM |
|
|
| This is a custom configuration (336M parameters) of Google’s Gemma 2 LLM that is being pre-trained on amino acid sequences of 512 AA or less in length. Periodic updates are made to this page as training reaches new checkpoints. |
|
|
|
|
| The purpose of this model was to investigate the differences between ProGemma and ProtGPT (GPT-2 architecture) as it pertains to sequence generation. Training loss is ~1.6. Perplexity scores as well as AlphaFold 3’s ptm, pLDDT, and iptm scores are generally in line with ProtGPT’s scores for sequence lengths < 250, although the testing phase is still very early. I have yet to do testing for sequence lengths > 250. More robust testing is also required for lengths < 250 AA. In my very preliminary testing, HHblit e-values of ~0.1 are achieved without much guidance. |
|
|
| Controlled generation is not a capability of this model, and therefore serves as a method to significantly improve generation as, in principal, a sequence that performs a given function or resides in a particular cellular location can be generated. |
|
|
| In sequence generation, a top_k of 950 appears to work well as it prevents repetition. This is also seen in ProtGPT. |
| |
| Below is code using the Transformers library to generate sequences using ProGemma. |
| |
| from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM |
| |
| model = AutoModelForCausalLM.from_pretrained("JuIm/ProGemma") |
|
|
| tokenizer = AutoTokenizer.from_pretrained("JuIm/Amino-Acid-Sequence-Tokenizer") |
| |
| progemma = pipeline("text-generation", model=model, tokenizer=tokenizer) |
| |
| sequence = progemma("\<bos>", top_k=950, max_length=100, num_return_sequences=1, do_sample=True, repetition_penalty=1.2, eos_token_id=21, pad_token_id=22, bos_token_id=20) |
| |
| s = sequence[0]['generated_text'] |
| |
| print(s) |
| |
| ### Framework versions |
| |
| - Transformers 4.44.2 |
| - Pytorch 2.4.0+cu121 |
| - Tokenizers 0.19.1 |
| |
