Mungert/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1-GGUF

GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1 GGUF Models

Model Generation Details

This model was generated using llama.cpp at commit 0a5a3b5c.

---

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 Summary:

This model is part of the GneissWeb ablations, detailed in this technical report. The model has 7 billion parameters and uses the LLama architecture. It is trained on a random subset of 350 billion English tokens from FineWeb.Edu.Score-2, tokenized using the StarCoder tokenizer.

• Developers: IBM Research

• Release Date: Feb 25th, 2025

• License: Apache 2.0

Intended Use:

This model is trained on 350B tokens of English FineWeb.Edu.Score2 data and is not instruction-tuned or safety aligned. It is important to note that the primary intended use case for this model is to compare its performance with other models trained under similar conditions, with the goal of comparing pre-training datasets. These other models are mentioned here

Generation:

This is a simple example of how to use GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1 model.

Install the following libraries:

pip install torch torchvision torchaudio
pip install accelerate
pip install transformers

Then, copy the code snippet below to run the example.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "auto"
model_path = "ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1"
tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()
# change input text as desired
input_text = "What is the meaning of 'Gneiss'?"
# tokenize the text
input_tokens = tokenizer(input_text, return_tensors="pt").to('cuda')
# generate output tokens
output = model.generate(**input_tokens,
                        max_length=35)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output)

Evaluation Results: Please refer to section 5.3.2 of the GneissWeb paper.

Infrastructure: Please refer to section 5.2 of the GneissWeb paper.

Ethical Considerations and Limitations: The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1 is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1 model with ethical intentions and in a responsible way.

Resources: Learn more about GneissWeb here.

---

🚀 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! 😊