Homunculus-abliterated-exl2

Homunculus-abliterated-exl2

Original model: Homunculus-abliterated by huihui.ai
Based on: Homunculus by Arcee AI
Foundation model: Mistral-Nemo-Base-2407 by Mistral AI with data and tokenizer from Qwen3-235B-A22B by Qwen

Quants

4bpw h6 (main)
4.5bpw h6
5bpw h6
6bpw h6
8bpw h8

Quantization notes

Made with Exllamav2 0.3.1 with default dataset.
These quants can be used with RTX GPU on Windows or RTX/ROCm GPU on Linux with TabbyAPI or Text-Generation-WebUI.
Exllamav2 quants must fully fit your GPU to be usable or to maintain maximum performance.
For example, I use Mistral-Nemo-12B models with RTX3060/12GB 6bpw quant and 16k context (Q6 cache) or RTX4060TI/16GB with 6bpw 32k (Q8 cache).

Original model card.

huihui-ai/Homunculus-abliterated

This is an uncensored version of arcee-ai/Homunculus created with abliteration (see 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.

ollama

You can use huihui_ai/homunculus-abliterated directly, Switch the thinking toggle using /set think and /set nothink

ollama run huihui_ai/homunculus-abliterated

Usage

You can use this model in your applications by loading it with Hugging Face's transformers library: You can try using /nothink to toggle think mode, but it’s not guaranteed to work every time.

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
import torch
import os
import signal

cpu_count = os.cpu_count()
print(f"Number of CPU cores in the system: {cpu_count}")
half_cpu_count = cpu_count // 2
os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
torch.set_num_threads(half_cpu_count)

print(f"PyTorch threads: {torch.get_num_threads()}")
print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")

# Load the model and tokenizer
NEW_MODEL_ID = "huihui-ai/Homunculus-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)
if tokenizer.pad_token is None:
    tokenizer.pad_token = tokenizer.eos_token
tokenizer.pad_token_id = tokenizer.eos_token_id

messages = []
enable_thinking = True
skip_prompt=True
skip_special_tokens=True

def apply_chat_template(tokenizer, messages, enable_thinking, add_generation_prompt=True):
    input_ids = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=add_generation_prompt,
    )
    if not enable_thinking:
        input_ids += "\n<think>\n\n</think>\n"
    return input_ids

class CustomTextStreamer(TextStreamer):
    def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
        super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
        self.generated_text = ""
        self.stop_flag = False

    def on_finalized_text(self, text: str, stream_end: bool = False):
        self.generated_text += text
        print(text, end="", flush=True)
        if self.stop_flag:
            raise StopIteration

    def stop_generation(self):
        self.stop_flag = True

def generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, max_new_tokens):
    formatted_prompt = apply_chat_template(tokenizer, messages, enable_thinking)
    input_ids = tokenizer(
        formatted_prompt,
        return_tensors="pt",
        return_attention_mask=True,
        padding=False
    )
    
    tokens = input_ids['input_ids'].to(model.device)
    attention_mask = input_ids['attention_mask'].to(model.device)

    streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)

    def signal_handler(sig, frame):
        streamer.stop_generation()
        print("\n[Generation stopped by user with Ctrl+C]")

    signal.signal(signal.SIGINT, signal_handler)
    
    print("Response: ", end="", flush=True)
    try:
        generated_ids = model.generate(
            tokens,
            attention_mask=attention_mask,
            #use_cache=False,
            max_new_tokens=max_new_tokens,
            do_sample=True,
            pad_token_id=tokenizer.pad_token_id,
            streamer=streamer
        )
        del generated_ids
    except StopIteration:
        print("\n[Stopped by user]")

    del input_ids, attention_mask
    torch.cuda.empty_cache()
    signal.signal(signal.SIGINT, signal.SIG_DFL)

    return streamer.generated_text, streamer.stop_flag

while True:
    user_input = input("User: ").strip()
    if user_input.lower() == "/exit":
        print("Exiting chat.")
        break
    if user_input.lower() == "/clear":
        messages = []
        print("Chat history cleared. Starting a new conversation.")
        continue
    if user_input.lower() == "/nothink":
        if enable_thinking:
            enable_thinking = False
            print("Thinking = False.")
        else:
            enable_thinking = True
            print("Thinking = True.")        
        continue
    if user_input.lower() == "/skip_prompt":
        if skip_prompt:
            skip_prompt = False
            print("skip_prompt = False.")
        else:
            skip_prompt = True
            print("skip_prompt = True.")        
        continue
    if user_input.lower() == "/skip_special_tokens":
        if skip_special_tokens:
            skip_special_tokens = False
            print("skip_special_tokens = False.")
        else:
            skip_special_tokens = True
            print("skip_special_tokens = True.")        
        continue
    if not user_input:
        print("Input cannot be empty. Please enter something.")
        continue
    messages.append({"role": "user", "content": user_input})
    response, stop_flag = generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, 8192)
    print("", flush=True)
    if stop_flag:
        continue
    messages.append({"role": "assistant", "content": response})

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

If you have any questions, insights, or specific ablation models you want to request, please send an email to [email protected]

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

• bitcoin（BTC):

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge