legraphista's picture
Upload README.md with huggingface_hub
b9aea4b verified
metadata
base_model: microsoft/Phi-3-mini-128k-instruct
inference: false
language:
  - en
library_name: gguf
license: mit
license_link: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

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


Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-mini-128k-instruct.Q8_0.gguf Q8_0 4.06GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-mini-128k-instruct.Q6_K.gguf Q6_K 3.14GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-mini-128k-instruct.Q4_K.gguf Q4_K 2.39GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.Q3_K.gguf Q3_K 1.96GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.Q2_K.gguf Q2_K 1.42GB βœ… Available 🟒 Yes πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-mini-128k-instruct.FP16.gguf F16 7.64GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-mini-128k-instruct.BF16.gguf BF16 7.64GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-mini-128k-instruct.Q5_K.gguf Q5_K 2.82GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-mini-128k-instruct.Q5_K_S.gguf Q5_K_S 2.64GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-mini-128k-instruct.Q4_K_S.gguf Q4_K_S 2.19GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.Q3_K_L.gguf Q3_K_L 2.09GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.Q3_K_S.gguf Q3_K_S 1.68GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.Q2_K_S.gguf Q2_K_S 1.33GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ4_NL.gguf IQ4_NL 2.18GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ4_XS.gguf IQ4_XS 2.06GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ3_M.gguf IQ3_M 1.86GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ3_S.gguf IQ3_S 1.68GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ3_XS.gguf IQ3_XS 1.63GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ3_XXS.gguf IQ3_XXS 1.51GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ2_M.gguf IQ2_M 1.32GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ2_S.gguf IQ2_S 1.22GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ2_XS.gguf IQ2_XS 1.15GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ2_XXS.gguf IQ2_XXS 1.04GB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ1_M.gguf IQ1_M 917.11MB βœ… Available 🟒 Yes πŸ“¦ No
Phi-3-mini-128k-instruct.IQ1_S.gguf IQ1_S 841.61MB βœ… Available 🟒 Yes πŸ“¦ No

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
  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!