初始化项目，由ModelHub XC社区提供模型

Model: McClain/PlasmidGPT-RL
Source: Original Platform

.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

README.md

@@ -0,0 +1,76 @@
+---
+base_model: UCL-CSSB/PlasmidGPT-SFT
+library_name: transformers
+model_name: PlasmidGPT-RL
+tags:
+- generated_from_trainer
+- grpo
+- trl
+- plasmid
+- biology
+- dna
+license: mit
+---
+
+# PlasmidGPT-RL
+
+This model is a fine-tuned version of [UCL-CSSB/PlasmidGPT-SFT](https://huggingface.co/UCL-CSSB/PlasmidGPT-SFT) using Group Relative Policy Optimization (GRPO).
+
+## Model Description
+
+PlasmidGPT-RL is trained to generate functional plasmid DNA sequences. It was fine-tuned using reinforcement learning with a reward model that evaluates:
+- Presence of valid origins of replication (OriV)
+- Presence of antibiotic resistance genes (ARGs)
+- Absence of problematic repeat sequences
+
+## Training
+
+This model was trained with GRPO using the [TRL library](https://github.com/huggingface/trl).
+
+**Training run**: [Weights & Biases](https://wandb.ai/ucl-cssb/PlasmidRL/runs/4e783zua)
+
+### Training Details
+- **Base model**: UCL-CSSB/PlasmidGPT-SFT
+- **Method**: GRPO (Group Relative Policy Optimization)
+- **Checkpoint**: 800 steps
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("McClain/PlasmidGPT-RL")
+model = AutoModelForCausalLM.from_pretrained("McClain/PlasmidGPT-RL")
+
+# Generate a plasmid sequence
+prompt = "ATG"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(
+    inputs.input_ids,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.95,
+    top_p=0.9
+)
+sequence = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(sequence)
+```
+
+## Framework Versions
+
+- TRL: 0.23.1
+- Transformers: 4.57.0
+- PyTorch: 2.8.0
+
+## Citation
+
+If you use this model, please cite the GRPO paper:
+
+```bibtex
+@article{shao2024deepseekmath,
+    title={{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author={Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year={2024},
+    eprint={arXiv:2402.03300},
+}
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 30000,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 30001,
+  "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,
+  "pad_token_id": 3,
+  "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
+    }
+  },
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 30002
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30000,
+  "eos_token_id": [
+    30001
+  ],
+  "pad_token_id": 3,
+  "transformers_version": "4.57.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cde5d397ae479478770b59033fcb8c7bcf72569bb3e324b67572e47617ba0d
+size 438696576

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]"
+}

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "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": "</s>",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}