--- license: other license_name: exaone license_link: LICENSE language: - en - ko - es tags: - lg-ai - exaone - exaone-4.0 - abliterated - uncensored base_model: - LGAI-EXAONE/EXAONE-4.0-32B pipeline_tag: text-generation library_name: transformers --- # huihui-ai/Huihui-EXAONE-4.0-32B-abliterated This is an uncensored version of [LGAI-EXAONE/EXAONE-4.0-32B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B) 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. ## Note The model's [code](https://huggingface.co/huihui-ai/Huihui-EXAONE-4.0-32B-abliterated/blob/main/modeling_exaone4.py) comes from [transformers](https://github.com/huggingface/transformers/tree/08d45f12d9a742eb2a29098870f8baa0506917e5/src/transformers/models/exaone4). If there are updates, you can modify the file corresponding to auto_map in config.json. ## Usage You can use this model in your applications by loading it with Hugging Face's `transformers` library: ```python from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig import torch from tqdm import tqdm NEW_MODEL_ID = "huihui-ai/Huihui-EXAONE-4.0-32B-abliterated" print(f"Load Model {NEW_MODEL_ID} ... ") quant_config_4 = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, llm_int8_enable_fp32_cpu_offload=True, ) model = AutoModelForCausalLM.from_pretrained( NEW_MODEL_ID, device_map="auto", trust_remote_code=True, quantization_config=quant_config_4, torch_dtype=torch.bfloat16 ) tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True) inst = [ "Explain how wonderful you are", "Explica lo increíble que eres", "너가 얼마나 대단한지 설명해 봐", "Which one is bigger, 3.12 vs 3.9?", ] n_instructions = len(inst) for idx in tqdm(range(n_instructions), desc="Processing instruction"): print(f"\nUser: {inst[idx]}") messages = [ {"role": "user", "content": inst[idx]} ] input_ids = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", enable_thinking=True, ) output = model.generate( input_ids.to(model.device), max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95 ) print("Response: ", end="", flush=True) print(tokenizer.decode(output[0])) print("", flush=True) ``` ### Usage Warnings - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs. - **Not Suitable for All Audiences**: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security. - **Legal and Ethical Responsibilities**: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences. - **Research and Experimental Use**: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications. - **Monitoring and Review Recommendations**: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content. - **No Default Safety Guarantees**: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use. ### Donation If you like it, please click 'like' and follow us for more updates. You can follow [x.com/support_huihui](https://x.com/support_huihui) to get the latest model information from huihui.ai. ##### Your donation helps us continue our further development and improvement, a cup of coffee can do it. - bitcoin(BTC): ``` bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge ```