初始化项目，由ModelHub XC社区提供模型

Model: npanium/deepseek-r1-qwen7b-smartcontract-grpo
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,192 @@
+---
+library_name: transformers
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tags:
+  - smart-contracts
+  - solidity
+  - security
+  - vulnerability-detection
+  - grpo
+  - lora
+  - reinforcement-learning
+language:
+  - en
+license: mit
+---
+
+# DeepSeek-R1-Distill-Qwen-7B — Smart Contract Vulnerability Detection
+
+RL fine-tuned version of DeepSeek-R1-Distill-Qwen-7B for detecting vulnerabilities in Solidity smart contracts. Fine-tuned using GRPO (Group Relative Policy Optimization) with LoRA on the CGT (Consolidated Ground Truth) dataset.
+
+---
+
+## Model Description
+
+- **Base model:** deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+- **Fine-tuning method:** GRPO + LoRA
+- **Task:** Smart contract vulnerability detection and classification
+- **Developer:** Nishant Pandav ([@npanium](https://github.com/npanium))
+- **Repository:** [https://github.com/npanium/smartcontracts-vulnerability-r1](https://github.com/npanium/smartcontracts-vulnerability-r1)
+- **License:** MIT
+
+---
+
+## What it does
+
+Given a Solidity smart contract, the model:
+1. Reasons through the code using chain-of-thought inside `<think>` tags
+2. Determines whether the contract is vulnerable
+3. Classifies the vulnerability by DASP category (1–9) and SWC ID (100–136)
+
+Output format:
+```
+<think>
+... reasoning about the contract ...
+</think>
+VULNERABLE: yes/no
+DASP_CATEGORY: N
+SWC_ID: NNN
+EXPLANATION: ...
+```
+
+---
+
+## Results
+
+Evaluated on 1,478 held-out contracts from the CGT dataset:
+
+| Metric | Before (base) | After (fine-tuned) | Delta |
+|--------|--------------|-------------------|-------|
+| Detection accuracy (Tier 1) | 23.0% | 74.3% | **+51.3%** |
+| DASP category (Tier 2) | 8.8% | 11.3% | +2.5% |
+| SWC ID (Tier 3) | 3.0% | 0.0% | -3.0% |
+| Overall | 11.6% | 28.5% | **+16.9%** |
+| Parse failure rate | 40.2% | 0.0% | **-40.2%** |
+
+---
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "npanium/deepseek-r1-qwen7b-smartcontract-grpo"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+contract = """
+pragma solidity ^0.4.18;
+contract Vulnerable {
+    mapping(address => uint) public balances;
+
+    function withdraw(uint _amount) public {
+        if (balances[msg.sender] >= _amount) {
+            msg.sender.call.value(_amount)();
+            balances[msg.sender] -= _amount;
+        }
+    }
+}
+"""
+
+prompt = f"""Analyze this Solidity smart contract for security vulnerabilities.
+Think step by step inside <think> tags, then provide your assessment.
+
+``solidity
+{contract}``
+
+
+Use this exact format:
+VULNERABLE: yes/no
+DASP_CATEGORY: [1-9]
+SWC_ID: [100-136]
+EXPLANATION: [one sentence]"""
+
+messages = [{"role": "user", "content": prompt}]
+inputs = tokenizer.apply_chat_template(
+    messages,
+    return_tensors="pt",
+    add_generation_prompt=True,
+)
+if hasattr(inputs, "input_ids"):
+    inputs = inputs.input_ids
+inputs = inputs.to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        inputs,
+        max_new_tokens=1024,
+        temperature=0.1,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+
+response = tokenizer.decode(
+    outputs[0][inputs.shape[1]:],
+    skip_special_tokens=True,
+)
+print(response)
+```
+
+---
+
+## Training Details
+
+### Dataset
+
+**CGT (Consolidated Ground Truth)** — [github.com/gsalzer/cgt](https://github.com/gsalzer/cgt)
+
+Consolidates 13 prior smart contract vulnerability datasets. Labels cross-validated across source datasets.
+
+| Split | Examples |
+|-------|----------|
+| Train | 5,910 |
+| Test (locked) | 1,478 |
+
+### Training Hyperparameters
+
+| Parameter | Value |
+|-----------|-------|
+| Training regime | bf16 mixed precision |
+| Learning rate | 5e-6 |
+| LoRA rank | 16 |
+| LoRA alpha | 32 |
+| LoRA target modules | q_proj, v_proj, k_proj, o_proj |
+| Generations per prompt | 8 |
+| Max completion length | 1024 |
+| Gradient accumulation steps | 8 |
+| Epochs | 1 |
+
+### Hardware
+
+- **GPU:** NVIDIA A100 SXM4 80GB
+- **Cloud provider:** Fluence Network
+- **Training duration:** ~48 hours
+
+---
+
+## Limitations
+
+**Outcome reward only.** The reward function validates whether the final label is correct, not whether the reasoning is valid. The model may produce plausible-sounding analysis that doesn't actually justify the conclusion.
+
+**SWC ID regression.** Post-training SWC ID accuracy dropped to zero. The model prioritised the higher-weighted binary detection reward at the expense of fine-grained weakness classification.
+
+**Context window.** Contracts exceeding ~4,000 characters were excluded from training. Performance on very large contracts is untested.
+
+---
+
+## Citation
+
+```bibtex
+@misc{pandav2026scvulnrl,
+  author = {Pandav, Nishant},
+  title  = {Smart Contract Vulnerability Detection via RL Fine-Tuning},
+  year   = {2026},
+  url    = {https://github.com/npanium/smartcontracts-vulnerability-r1}
+}
+```

chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f870ae6b1169e03774feb6ec0d28fa34980f35f573e34ce18905b7f473a1cfb9
+size 15231272152

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
+size 11421911

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}