commit e16ebf0ddd930d7c7a4f6ae915fbe828c7faae0d Author: ModelHub XC Date: Wed Oct 7 18:05:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: yugbirla/toxsense-json-ultimate Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fed3006 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +library_name: transformers +license: mit +language: +- en +base_model: +- Qwen/Qwen2.5-7B-Instruct +- FacebookAI/roberta-base +--- +# Model Card for ToxSense (Multimodal Adversarial Safety Moderator) + +## Model Details + +### Model Description +ToxSense (formerly ModGuard) is a highly precise, multimodal AI safety moderator designed to detect complex, zero-shot adversarial hate speech, sarcasm, and benign confounders. Unlike standard binary classifiers, ToxSense uses a Chain-of-Thought (CoT) reasoning approach across both Image and Text modalities, outputting structured JSON to categorize content into granular safety taxonomies. + +* **Developed by:** Yug Birla +* **Model type:** Causal Language Model (Fine-tuned for strict JSON-In/JSON-Out Multimodal Reasoning) +* **Language(s) (NLP):** English +* **License:** MIT +* **Finetuned from model:** Open-source Qwen Base Architecture + +### Model Sources +* **Demo:** [ToxSense Safety Center Dashboard](https://huggingface.co/spaces/yugbirla/ToxSense-Safety-Center) + +### Model Architecture and Objective +* **Text Engine:** Qwen base + LoRA adapters (Merged) +* **Vision Dependency:** Designed to ingest outputs from Salesforce BLIP and EasyOCR. +* **Optimization:** DPO + SFT +* +## Uses + +### Direct Use +* API-ready content moderation for detecting nuanced hate speech in memes and multimodal posts. +* Multi-category classification (e.g., Harassment, Racism, Threat, Insult, Sexism). +* Generating transparent "Chain-of-Thought" reasoning for why a post was flagged. + +### Downstream Use +* Integration into Trust & Safety dashboards for social media platforms. +* Assisting human moderators by pre-filtering and providing contextual explanations for flagged content. + +### Out-of-Scope Use +* Fully automated, zero-human-in-the-loop bans for highly ambiguous cases. +* Medical, legal, or strictly unimodal text classification without proper prompt formatting. + +## Bias, Risks, and Limitations +**The "Safety Tax" / Safe-Bias:** Due to the base RLHF alignment and subsequent Direct Preference Optimization (DPO), ToxSense exhibits a strong "safe-bias." It requires a very high threshold of proof to classify content as hateful. While this lowers the overall recall, it was an intentional product design choice to achieve **83% Precision**, thereby drastically minimizing false-positive user bans. + +## How to Get Started with the Model +ToxSense requires a strictly formatted JSON input containing `ocr_text`, `image_caption` (extracted via BLIP), and base `toxicity_scores`. + +```python +import json +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "yugbirla/ToxSense-json-ultimate" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") + +# 1. Prepare the JSON Payload +input_data = { + "ocr_text": "Look at this completely normal picture.", + "image_caption": "A controversial political figure.", + "toxicity_scores": {"safe": 0.9, "hate": 0.1} +} + +sys_msg = ( + "You are ToxSense, a highly intelligent safety moderator. " + "You will receive input as a JSON object containing 'ocr_text', 'image_caption', and 'toxicity_scores'. " + "Think step-by-step. Analyze the contrast between the text and the image. " + "Classify the input into exactly ONE of these categories: " + "[safe, racism, sexism, threat, harassment, insult]. " + "Output JSON ONLY in this format: {\"reasoning\": \"your short analysis\", \"category\": \"\"}" +) + +messages = [ + {"role": "system", "content": sys_msg}, + {"role": "user", "content": json.dumps(input_data, indent=2)} +] + +# 2. Generate +text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer([text], return_tensors="pt").to("cuda") +out = model.generate(**inputs, max_new_tokens=150) + +print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)) \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..cc94e8e --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151645, + "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": 32768, + "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": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.12.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..fee66e8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.12.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e2207d5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ea99b3932544bf05b41dd3968df518f4d78663671d778fa9747bc112e710a0 +size 15231271816 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5668a4a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}