Mungert/Llama3-ChatQA-2-8B-GGUF

Llama3-ChatQA-2-8B GGUF Models

Model Generation Details

This model was generated using llama.cpp at commit e743cddb.

---

Quantization Beyond the IMatrix

I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.

In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision. You can see the implementation here:
👉 Layer bumping with llama.cpp

While this does increase model file size, it significantly improves precision for a given quantization level.

I'd love your feedback—have you tried this? How does it perform for you?

---

Click here to get info on choosing the right GGUF model format

---

Model Details

We introduce Llama3-ChatQA-2, a suite of 128K long-context models, which bridges the gap between open-source LLMs and leading proprietary models (e.g., GPT-4-Turbo) in long-context understanding and retrieval-augmented generation (RAG) capabilities. Llama3-ChatQA-2 is developed using an improved training recipe from ChatQA-1.5 paper, and it is built on top of Llama-3 base model. Specifically, we continued training of Llama-3 base models to extend the context window from 8K to 128K tokens, along with a three-stage instruction tuning process to enhance the model’s instruction-following, RAG performance, and long-context understanding capabilities. Llama3-ChatQA-2 has two variants: Llama3-ChatQA-2-8B and Llama3-ChatQA-2-70B. Both models were originally trained using Megatron-LM, we converted the checkpoints to Hugging Face format. For more information about ChatQA 2, check the website!

Other Resources

Llama3-ChatQA-2-70B   Evaluation Data   Training Data   Website   Paper

Overview of Benchmark Results

We evaluate ChatQA 2 on short-context RAG benchmark (ChatRAG) (within 4K tokens), long context tasks from SCROLLS and LongBench (within 32K tokens), and ultra-long context tasks from In- finiteBench (beyond 100K tokens). Results are shown below.

Note that ChatQA-2 is built based on Llama-3 base model.

Prompt Format

We highly recommend that you use the prompt format we provide, as follows:

when context is available

System: {System}

{Context}

User: {Question}

Assistant: {Response}

User: {Question}

Assistant:

when context is not available

System: {System}

User: {Question}

Assistant: {Response}

User: {Question}

Assistant:

The content of the system's turn (i.e., {System}) for both scenarios is as follows:

This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context.

Note that our ChatQA-2 models are optimized for the capability with context, e.g., over documents or retrieved context.

How to use

take the whole document as context

This can be applied to the scenario where the whole document can be fitted into the model, so that there is no need to run retrieval over the document.

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "nvidia/Llama3-ChatQA-2-8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

messages = [
    {"role": "user", "content": "what is the percentage change of the net income from Q4 FY23 to Q4 FY24?"}
]

document = """NVIDIA (NASDAQ: NVDA) today reported revenue for the fourth quarter ended January 28, 2024, of $22.1 billion, up 22% from the previous quarter and up 265% from a year ago.\nFor the quarter, GAAP earnings per diluted share was $4.93, up 33% from the previous quarter and up 765% from a year ago. Non-GAAP earnings per diluted share was $5.16, up 28% from the previous quarter and up 486% from a year ago.\nQ4 Fiscal 2024 Summary\nGAAP\n| $ in millions, except earnings per share | Q4 FY24 | Q3 FY24 | Q4 FY23 | Q/Q | Y/Y |\n| Revenue | $22,103 | $18,120 | $6,051 | Up 22% | Up 265% |\n| Gross margin | 76.0% | 74.0% | 63.3% | Up 2.0 pts | Up 12.7 pts |\n| Operating expenses | $3,176 | $2,983 | $2,576 | Up 6% | Up 23% |\n| Operating income | $13,615 | $10,417 | $1,257 | Up 31% | Up 983% |\n| Net income | $12,285 | $9,243 | $1,414 | Up 33% | Up 769% |\n| Diluted earnings per share | $4.93 | $3.71 | $0.57 | Up 33% | Up 765% |"""

def get_formatted_input(messages, context):
    system = "System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context."
    instruction = "Please give a full and complete answer for the question."

    for item in messages:
        if item['role'] == "user":
            ## only apply this instruction for the first user turn
            item['content'] = instruction + " " + item['content']
            break

    conversation = '\n\n'.join(["User: " + item["content"] if item["role"] == "user" else "Assistant: " + item["content"] for item in messages]) + "\n\nAssistant:"
    formatted_input = system + "\n\n" + context + "\n\n" + conversation
    
    return formatted_input

formatted_input = get_formatted_input(messages, document)
tokenized_prompt = tokenizer(tokenizer.bos_token + formatted_input, return_tensors="pt").to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(input_ids=tokenized_prompt.input_ids, attention_mask=tokenized_prompt.attention_mask, max_new_tokens=128, eos_token_id=terminators)

response = outputs[0][tokenized_prompt.input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Command to run generation

python evaluate_cqa_vllm_chatqa2.py --model-folder ${model_path} --eval-dataset ${dataset_name} --start-idx 0 --end-idx ${num_samples} --max-tokens ${max_tokens} --sample-input-file ${dataset_path}

see all_command.sh for all detailed configuration.

Correspondence to

Peng Xu ([email protected]), Wei Ping ([email protected])

Citation

@article{xu2024chatqa,
  title={ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities},
  author={Xu, Peng and Ping, Wei and Wu, Xianchao and Liu, Zihan and Shoeybi, Mohammad and Catanzaro, Bryan},
  journal={arXiv preprint arXiv:2407.14482},
  year={2024}
}

License

The Model is released under Non-Commercial License and the use of this model is also governed by the META LLAMA 3 COMMUNITY LICENSE AGREEMENT

---

🚀 If you find these models useful

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:
Choose an AI assistant type:

• TurboLLM (GPT-4.1-mini)
• HugLLM (Hugginface Open-source models)
• TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

• Function calling against live network services
• How small can a model go while still handling:
  • Automated Nmap security scans
  • Quantum-readiness checks
  • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

• ✅ Zero-configuration setup
• ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
• 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

• **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
• Create custom cmd processors to run .net code on Quantum Network Monitor Agents
• Real-time network diagnostics and monitoring
• Security Audits
• Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

• 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

1. "Give me info on my websites SSL certificate"
2. "Check if my server is using quantum safe encyption for communication"
3. "Run a comprehensive security audit on my server"
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊