---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
base_model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
tags:
- chat
- abliterated
- uncensored
---
# Qwen2.5-14B-Instruct-abliterated-v2-exl2
Model: [Qwen2.5-14B-Instruct-abliterated-v2](https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2)  
Made by: [huihui-ai](https://huggingface.co/huihui-ai)
## Quants
[4bpw h6 (main)](https://huggingface.co/cgus/Qwen2.5-14B-Instruct-abliterated-v2-exl2/tree/main)  
[4.5bpw h6](https://huggingface.co/cgus/Qwen2.5-14B-Instruct-abliterated-v2-exl2/tree/4.5bpw-h6)  
[5bpw h6](https://huggingface.co/cgus/Qwen2.5-14B-Instruct-abliterated-v2-exl2/tree/5bpw-h6)  
[6bpw h6](https://huggingface.co/cgus/Qwen2.5-14B-Instruct-abliterated-v2-exl2/tree/6bpw-h6)  
[8bpw h8](https://huggingface.co/cgus/Qwen2.5-14B-Instruct-abliterated-v2-exl2/tree/8bpw-h8)  
## Quantization notes
Made with exllamav2 0.2.3 with the default dataset.  
Exl2 quants can be used with Nvidia RTX2xxx or newer GPUs on Windows/Linux or AMD on Linux.  
This model format works the best when a model fits your GPU, otherwise it's better to use GGUF versions.  
For example with RTX3060/12GB I could fit 4.5bpw/5bpw with Q6 cache and 16k context.  
Use with with Text-Generation-WebUI, TabbyAPI or other apps that have exllamav2 loader.

# Original model card
# huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2


This is an uncensored version of [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).

Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.

**Important Note** This version is an improvement over the previous one [Qwen2.5-14B-Instruct-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-abliterated).

## Usage
You can use this model in your applications by loading it with Hugging Face's `transformers` library:


```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Initialize conversation context
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

# Enter conversation loop
while True:
    # Get user input
    user_input = input("User: ").strip()  # Strip leading and trailing spaces

    # If the user types '/exit', end the conversation
    if user_input.lower() == "/exit":
        print("Exiting chat.")
        break

    # If the user types '/clean', reset the conversation context
    if user_input.lower() == "/clean":
        messages = initial_messages.copy()  # Reset conversation context
        print("Chat history cleared. Starting a new conversation.")
        continue

    # If input is empty, prompt the user and continue
    if not user_input:
        print("Input cannot be empty. Please enter something.")
        continue

    # Add user input to the conversation
    messages.append({"role": "user", "content": user_input})

    # Build the chat template
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )

    # Tokenize input and prepare it for the model
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    # Generate a response from the model
    generated_ids = model.generate(
        **model_inputs,
        max_new_tokens=8192
    )

    # Extract model output, removing special tokens
    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]

    # Add the model's response to the conversation
    messages.append({"role": "assistant", "content": response})

    # Print the model's response
    print(f"Qwen: {response}")

```

## Evaluations
Evaluation is ongoing, to be continued later.