commit 8ab1771c23cc25b9d75daf3bd4f542f5e4f329e8 Author: ModelHub XC Date: Wed Aug 5 23:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: AI4PD/ProtGPT3-1.3B-dpo Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..02fd0c4 --- /dev/null +++ b/README.md @@ -0,0 +1,57 @@ +--- +library_name: transformers +tags: +- biology +- protein-language-model +- protein-generation +- causal-lm +- mixture-of-experts +- transformers +- dpo +- alignment +- protein-design +--- + +# Model Card for ProtGPT3-1.3B-dpo + + +## Model Description +ProtGPT3-1.3M-dpo is the DPO-aligned version of [ProtGPT3-1.3B](https://huggingface.co/AI4PD/ProtGPT3-1.3B). It is part of the [ProtGPT3 family](https://huggingface.co/collections/AI4PD/protgpt3-family), an open-source suite of promptable and aligned protein language models for protein design. + +ProtGPT3-1.3M-dpo was further aligned with Direct Preference Optimization (DPO) to improve generation quality. The alignment procedure shifts the model toward protein sequences with higher predicted structural confidence and reduced low-complexity content, while preserving sequence diversity. +For protein generation, each model -dpo version is recommended over the base model. + +For more info and guidance on how to generate sequences with ProtGPT3-1.3B-dpo check out the extensive description provided in [ProtGPT3-1.3B](https://huggingface.co/AI4PD/ProtGPT3-1.3B), just replacing the model name (i.e., `model_name=AI4PD/ProtGPT3-1.3B-dpo`). + +## Out-of-Scope Use + +The model should not be used as the sole basis for experimental, clinical, environmental, or safety-critical decisions. Generated sequences require downstream computational and experimental validation. The model is not guaranteed to generate functional, soluble, safe, synthesizable, or experimentally successful proteins. + +The model should not be used for irresponsible or harmful biological design applications. + +## Bias, Risks, and Limitations + +ProtGPT3-1.3B-dpo learns from public protein sequence datasets and may reproduce biases present in those datasets. Although DPO alignment reduces low-complexity generations and improves generation quality according to the alignment objectives (pLDDT and reduction of lcr, as a binary objective, see main manuscript), generated sequences may still be nonfunctional, unstable, insoluble, repetitive, biologically implausible, or unsuitable for a user’s intended application. + +The DPO alignment objective uses predicted structural confidence and low-complexity filtering as proxy objectives. These proxies do not guarantee biological function, experimental success, safety, solubility, or manufacturability. + +As with other generative protein models, ProtGPT3-1.3B-dpo may present dual-use risks if applied irresponsibly. + + +## Citation + +**BibTeX:** + +```bibtex +@article{protgpt3, + title={ProtGPT3: an Open-source family of Promptable and Aligned Protein Language Models}, + author={Anonymous Authors}, + year={2026} +} +``` + +## More Information + +For more info and guidance on how to generate sequences with ProtGPT3-112M-dpo check out the extensive description provided in [ProtGPT3-1.3B](https://huggingface.co/AI4PD/ProtGPT3-1.3B), just replacing the model name (i.e., `model_name=AI4PD/ProtGPT3-1.3B-dpo`). + + diff --git a/config.json b/config.json new file mode 100644 index 0000000..776efc9 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": null, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "max_position_embeddings": 16384, + "model_type": "mixtral", + "num_attention_heads": 16, + "num_experts_per_tok": 2, + "num_hidden_layers": 17, + "num_key_value_heads": 4, + "num_local_experts": 8, + "output_router_logits": false, + "pad_token_id": 0, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.53.3", + "use_cache": true, + "vocab_size": 31 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b1bed96 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": [ + 2 + ], + "pad_token_id": 0, + "transformers_version": "4.53.3" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..62ce5a5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048f0dc74bd6b3cf6aa00aa7f91b00b8a23174f309bd2b898f593442ad2b5235 +size 2656587200 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..40936f5 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|bos|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eos|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..2d92c24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,143 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "content": "<|pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "<|bos|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "<|eos|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 31, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 32, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 33, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + ], + "normalizer": null, + "pre_tokenizer": { + "type": "Split", + "pattern": { + "String": "" + }, + "behavior": "Isolated", + "invert": false + }, + "post_processor": { + "type": "TemplateProcessing", + "single": [ + { + "Sequence": { + "id": "A", + "type_id": 0 + } + } + ], + "pair": [ + { + "Sequence": { + "id": "A", + "type_id": 0 + } + }, + { + "Sequence": { + "id": "B", + "type_id": 1 + } + } + ], + "special_tokens": {} + }, + "decoder": null, + "model": { + "type": "WordLevel", + "vocab": { + "<|pad|>": 0, + "<|bos|>": 1, + "<|eos|>": 2, + "[UNK]": 3, + "1": 4, + "2": 5, + "A": 6, + "B": 7, + "C": 8, + "D": 9, + "E": 10, + "F": 11, + "G": 12, + "H": 13, + "I": 14, + "K": 15, + "L": 16, + "M": 17, + "N": 18, + "O": 19, + "P": 20, + "Q": 21, + "R": 22, + "S": 23, + "T": 24, + "U": 25, + "V": 26, + "W": 27, + "X": 28, + "Y": 29, + "Z": 30 + }, + "unk_token": "[UNK]" + } +} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..92162ad --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,73 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "0": { + "content": "<|pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|bos|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|eos|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "[UNK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|bos|>", + "clean_up_tokenization_spaces": false, + "eos_token": "<|eos|>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 1025, + "pad_token": "<|pad|>", + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": "", + "use_default_system_prompt": false +}