初始化项目，由ModelHub XC社区提供模型

Model: UCL-CSSB/PlasmidGPT
Source: Original Platform

.gitattributes

@@ -0,0 +1 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- biology
+- plasmid
+- dna
+- synthetic-biology
+- gpt2
+---
+
+# PlasmidGPT
+
+A HuggingFace-compatible repackaging of [PlasmidGPT](https://github.com/lingxusb/PlasmidGPT) (Shao, 2024) — a GPT-2-style decoder pretrained on 153k engineered plasmid sequences from Addgene. Loadable with standard `AutoModelForCausalLM` and `AutoTokenizer`. Used as the base for [PlasmidGPT-SFT](https://huggingface.co/UCL-CSSB/PlasmidGPT-SFT) and [PlasmidGPT-GRPO](https://huggingface.co/UCL-CSSB/PlasmidGPT-GRPO).
+
+## Quick start
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("UCL-CSSB/PlasmidGPT")
+tokenizer = AutoTokenizer.from_pretrained("UCL-CSSB/PlasmidGPT")
+
+input_ids = tokenizer("ATG", return_tensors="pt").input_ids
+outputs = model.generate(input_ids, max_new_tokens=512, do_sample=True, temperature=1.0)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Citation
+
+```bibtex
+@article{shao2024plasmidgpt,
+  title   = {{PlasmidGPT}: a generative framework for plasmid design and annotation},
+  author  = {Shao, Bin},
+  journal = {bioRxiv},
+  year    = {2024},
+  doi     = {10.1101/2024.09.30.615762}
+}
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "use_cache": true,
+  "vocab_size": 30002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02365cb1aa0e86be0439567e7a8d15b51234dfdc051025ab1b2e4b157923debb
+size 438696576

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_generation.py

@@ -0,0 +1,35 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+print(f"Using device: {device}")
+
+model = AutoModelForCausalLM.from_pretrained(
+    "/Users/mcclainthiel/plasmidgpt-addgene-gpt2",
+    trust_remote_code=True
+).to(device)
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(
+    "/Users/mcclainthiel/plasmidgpt-addgene-gpt2",
+    trust_remote_code=True
+)
+
+start_sequence = 'ATGGCTAGCGAATTCGGCGCGCCT'
+print(f"Start sequence: {start_sequence}\n")
+
+input_ids = tokenizer.encode(start_sequence, return_tensors='pt').to(device)
+
+outputs = model.generate(
+    input_ids,
+    max_length=300,
+    num_return_sequences=1,
+    temperature=1.0,
+    do_sample=True,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+generated_sequence = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(f"Generated sequence:\n{generated_sequence}\n")
+print(f"Length: {len(generated_sequence)} bp")

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}