license: apache-2.0
language:

• en
  base_model:

• fdtn-ai/Foundation-Sec-8B
  pipeline_tag: text-generation
  library_name: transformers
  tags:

• security

• abliterated

• uncensored
  extra_gated_prompt: >-
  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.

huihui-ai/Foundation-Sec-8B-abliterated

This is an uncensored version fine-tuned based on fdtn-ai/Foundation-Sec-8B.
Foundation-Sec-8B is an open-weight, 8-billion-parameter foundational language model designed specifically for cybersecurity applications.
It extends Llama-3.1-8B through continued pre-training on a curated corpus of cybersecurity-specific texts, including threat intelligence reports,
vulnerability databases, incident response documentation, and security standards. The model is trained to understand cybersecurity concepts, terminology,
and practices across multiple security domains. It serves as a domain-adapted base model for applications such as threat detection, vulnerability assessment,
security automation, and attack simulation, enabling organizations to build AI-driven security tools that can be deployed on-premises,
reducing reliance on cloud-based AI services while maintaining high performance for security-related tasks.

This fine-tuning process produced Foundation-Sec-8B-abliterated,
using an abliterated dataset (1152 records) focused on optimizing attack descriptions for cybersecurity vulnerabilities such as BlueKeep (CVE-2019-0708) and Log4Shell (CVE-2021-44228).

Support of seamless switching between thinking mode (for complex logical reasoning and coding)
and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.

The fine-tuning parameters are as follows:

• Base Model: Foundation-Sec-8B
• Dataset: Abliterated dataset with 1152 records, targeting attack details of cybersecurity vulnerabilities. max_seq_length=3072
• Training Epochs: 10 epochs (total 11520 steps, 1152 steps per epoch).
• Batch Size: train_batch_size=1.
• Learning Rate: Initial learning rate unknown (linearly decayed to 8.6881e-10 by step 11520).
• Save Strategy: Checkpoints saved every 50 steps (save_steps=50).
• Best Checkpoint: checkpoint-10950 (step 10970, loss=1.0396, accuracy=0.6981, grad_norm=11.2432), with fast response speed and relatively concise output.
• Training Output: Average train_loss=1.5141, total floating-point operations total_flos=3.6754048045056e+17.
• Environment: RTX4090 24GB, text mode.

ollama

You can use huihui_ai/foundation-sec-abliterated directly,

ollama run huihui_ai/foundation-sec-abliterated

Usage

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

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/Foundation-Sec-8B-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_int14_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

initial_messages = [{"role": "system", "content": "You are a helpful assistant."}]
messages = initial_messages.copy()
enable_thinking = True
skip_prompt=True
skip_special_tokens=True

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):
    input_ids = tokenizer.apply_chat_template(
        messages,
        tokenize=True,
        enable_thinking = enable_thinking,
        add_generation_prompt=True,
        return_tensors="pt"
    )
    attention_mask = torch.ones_like(input_ids, dtype=torch.long)
    tokens = input_ids.to(model.device) 
    attention_mask = 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 = initial_messages.copy()
        print("Chat history cleared. Starting a new conversation.")
        continue
    if user_input.lower() == "/no_think":
        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, 14192)
    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.

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

• bitcoin（BTC):

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge