Phi-3-mini-128k-instruct-IMat-GGUF

Phi-3-mini-128k-instruct-IMat-GGUF

Llama.cpp imatrix quantization of microsoft/Phi-3-mini-128k-instruct

Original Model: microsoft/Phi-3-mini-128k-instruct
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3003
IMatrix dataset: here

• Phi-3-mini-128k-instruct-IMat-GGUF
  • Files
    • IMatrix
    • Common Quants
    • All Quants
  • Downloading using huggingface-cli
  • Inference
    • Simple chat template
    • 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

If you do not have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/Phi-3-mini-128k-instruct-IMat-GGUF --include "Phi-3-mini-128k-instruct.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/Phi-3-mini-128k-instruct-IMat-GGUF --include "Phi-3-mini-128k-instruct.Q8_0/*" --local-dir Phi-3-mini-128k-instruct.Q8_0
# see FAQ for merging GGUF's

---

Inference

Simple chat template

<s><|user|>
Can you provide ways to eat combinations of bananas and dragonfruits?<|end|>
<|assistant|>
Sure! Here are some ways to eat bananas and dragonfruits together:
 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey.
 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey.<|end|>
<|user|>
What about solving an 2x + 3 = 7 equation?<|end|>
<|assistant|>

Llama.cpp

llama.cpp/main -m Phi-3-mini-128k-instruct.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: Phi-3-mini-128k-instruct.Q8_0)
3. Run gguf-split --merge Phi-3-mini-128k-instruct.Q8_0/Phi-3-mini-128k-instruct.Q8_0-00001-of-XXXXX.gguf Phi-3-mini-128k-instruct.Q8_0.gguf
   • Make sure to point gguf-split to the first chunk of the split.

---

Got a suggestion? Ping me @legraphista!