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?
Granite-20B-Code-Instruct-r1.1 is a 20B parameter model fine tuned from Granite-20B-Code-Instruct-r1.1 on a combination of permissively licensed instruction data to enhance instruction following capabilities including mathematical reasoning and problem-solving skills.
The model is designed to respond to coding related instructions and can be used to build coding assistants.
Generation
This is a simple example of how to use Granite-20B-Code-Instruct-r1.1 model.
python
1import torch
2from transformers import AutoModelForCausalLM, AutoTokenizer
3device ="cuda"# or "cpu"4model_path ="ibm-granite/granite-20b-code-instruct-r1.1"5tokenizer = AutoTokenizer.from_pretrained(model_path)6# drop device_map if running on CPU7model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)8model.eval()9# change input text as desired10chat =[11{"role":"user","content":"Write a code to find the maximum value in a list of numbers."},12]13chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)14# tokenize the text15input_tokens = tokenizer(chat, return_tensors="pt")16# transfer tokenized inputs to the device17for i in input_tokens:18 input_tokens[i]= input_tokens[i].to(device)19# generate output tokens20output = model.generate(**input_tokens, max_new_tokens=100)21# decode output tokens into text22output = tokenizer.batch_decode(output)23# loop over the batch to print, in this example the batch size is 124for i in output:25print(i)
Training Data
Granite Code Instruct models are trained on the following types of data.
Code Commits Datasets: we sourced code commits data from the CommitPackFT dataset, a filtered version of the full CommitPack dataset. From CommitPackFT dataset, we only consider data for 92 programming languages. Our inclusion criteria boils down to selecting programming languages common across CommitPackFT and the 116 languages that we considered to pretrain the code-base model (Granite-20B-Code-Base-r1.1).
Math Datasets: We consider two high-quality math datasets, MathInstruct and MetaMathQA. Due to license issues, we filtered out GSM8K-RFT and Camel-Math from MathInstruct dataset.
Language Instruction Datasets: We include high-quality datasets such as HelpSteer and an open license-filtered version of Platypus. We also include a collection of hardcoded prompts to ensure our model generates correct outputs given inquiries about its name or developers.
Infrastructure
We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.
Ethical Considerations and Limitations
Granite code instruct models are primarily finetuned using instruction-response pairs across a specific set of programming languages. Thus, their performance may be limited with out-of-domain programming languages. In this situation, it is beneficial providing few-shot examples to steer the model's output. Moreover, developers should perform safety testing and target-specific tuning before deploying these models on critical applications. The model also inherits ethical considerations and limitations from its base model. For more information, please refer to Granite-20B-Code-Base-r1.1 model card.
🚀 If you find these models useful
Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:
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:
"Give me info on my websites SSL certificate"
"Check if my server is using quantum safe encyption for communication"
"Run a comprehensive security audit on my server"
'"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.
