huihui-ai/Qwen2.5-72B-Instruct-abliterated

Qwen

This is an uncensored version of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. You can use [huihui_ai/qwen2.5-abliterate:72b](https://ollama.com/huihui_ai/qwen2.5-abliterate:72b) directly, ollama run huihui_ai/qwen2.5-abliterate:72b You can use this model in your applications by loading it with Hugging Face's `transformers` library: from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "huihui-ai/Qwen2.5-72B-Instruct-abliterated" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) initial_messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."} ] messages = initial_messages.copy() # Copy the initial conversation context while True: user_input = input("User: ").strip() # Strip leading and trailing spaces if user_input.lower() == "/exit": print("Exiting chat.") break if user_input.lower() == "/clean": messages = initial_messages.copy() # Reset conversation context print("Chat history cleared. Starting a new conversation.") continue if not user_input: print("Input cannot be empty. Please enter something.") continue messages.append({"role": "user", "content": user_input}) text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=8192 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] messages.append({"role": "assistant", "content": response}) print(f"Qwen: {response}") [open-llm-leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/)