Nxcode CQ 7B Orpo IMat GGUF

🚀 Nxcode-CQ-7B-orpo-IMat-GGUF

Llama.cpp imatrix quantization of NTQAI/Nxcode-CQ-7B-orpo

This project offers a quantized version of the NTQAI/Nxcode-CQ-7B-orpo model using llama.cpp's imatrix quantization. It provides various quantization types and offers guidance on downloading and inference.

Original Model: NTQAI/Nxcode-CQ-7B-orpo
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3067
IMatrix dataset: here

• Files
  • IMatrix
  • Common Quants
  • All Quants
• Downloading using huggingface-cli
• Inference
  • Simple chat template
  • Chat template with system prompt
  • Llama.cpp
• FAQ
  • Why is the IMatrix not applied everywhere?
  • How do I merge a split GGUF?

📦 Files

🔍 IMatrix

Status: ✅ Available
Link: here

📋 Common Quants

📋 All Quants

💻 Downloading using huggingface-cli

⚠️ Important Note

If you do not have hugginface-cli installed, you need to install it first.

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/Nxcode-CQ-7B-orpo-IMat-GGUF --include "Nxcode-CQ-7B-orpo.Q8_0.gguf" --local-dir ./

If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/Nxcode-CQ-7B-orpo-IMat-GGUF --include "Nxcode-CQ-7B-orpo.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

💻 Inference

💬 Simple chat template

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

💬 Chat template with system prompt

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

🐪 Llama.cpp

llama.cpp/main -m Nxcode-CQ-7B-orpo.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"

❓ FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

1. Make sure you have gguf-split available
   • To get hold of gguf-split, navigate to https://github.com/ggerganov/llama.cpp/releases
   • Download the appropriate zip for your system from the latest release
   • Unzip the archive and you should be able to find gguf-split
2. Locate your GGUF chunks folder (ex: Nxcode-CQ-7B-orpo.Q8_0)
3. Run gguf-split --merge Nxcode-CQ-7B-orpo.Q8_0/Nxcode-CQ-7B-orpo.Q8_0-00001-of-XXXXX.gguf Nxcode-CQ-7B-orpo.Q8_0.gguf
   • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!