Hugging Face's logo

legraphista
/
Phi-3-medium-128k-instruct-IMat-GGUF

Text Generation
GGUF
multilingual
quantized
GGUF
imatrix
quantization
imat
static
conversational
Model card Files Community
Phi-3-medium-128k-instruct-IMat-GGUF / README.md
legraphista's picture
legraphista
Upload README.md with huggingface_hub
e6d8735 verified
preview code
|
raw
history blame
8.74 kB
metadata
base_model: microsoft/Phi-3-medium-128k-instruct
inference: false
language:
  - multilingual
library_name: gguf
license: mit
license_link: >-
  https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

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

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

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

Files

IMatrix

Status: ✅ Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-medium-128k-instruct.Q8_0.gguf Q8_0 14.83GB ✅ Available ⚪ No 📦 No
Phi-3-medium-128k-instruct.Q6_K.gguf Q6_K 11.45GB ✅ Available ⚪ No 📦 No
Phi-3-medium-128k-instruct.Q4_K.gguf Q4_K 8.57GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.Q3_K.gguf Q3_K 6.92GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.Q2_K.gguf Q2_K 5.14GB ✅ Available 🟢 Yes 📦 No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-medium-128k-instruct.FP16.gguf F16 27.92GB ✅ Available ⚪ No 📦 No
Phi-3-medium-128k-instruct.BF16.gguf BF16 27.92GB ✅ Available ⚪ No 📦 No
Phi-3-medium-128k-instruct.Q5_K.gguf Q5_K 10.07GB ✅ Available ⚪ No 📦 No
Phi-3-medium-128k-instruct.Q5_K_S.gguf Q5_K_S 9.62GB ✅ Available ⚪ No 📦 No
Phi-3-medium-128k-instruct.Q4_K_S.gguf Q4_K_S 7.95GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.Q3_K_L.gguf Q3_K_L 7.49GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.Q3_K_S.gguf Q3_K_S 6.06GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.Q2_K_S.gguf Q2_K_S 4.77GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.IQ4_NL.gguf IQ4_NL 7.90GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.IQ4_XS.gguf IQ4_XS 7.47GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.IQ3_M.gguf IQ3_M 6.47GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.IQ3_S.gguf IQ3_S 6.06GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.IQ3_XS.gguf IQ3_XS 5.81GB ✅ Available 🟢 Yes 📦 No
Phi-3-medium-128k-instruct.IQ3_XXS IQ3_XXS - ⏳ Processing 🟢 Yes -
Phi-3-medium-128k-instruct.IQ2_M IQ2_M - ⏳ Processing 🟢 Yes -
Phi-3-medium-128k-instruct.IQ2_S IQ2_S - ⏳ Processing 🟢 Yes -
Phi-3-medium-128k-instruct.IQ2_XS IQ2_XS - ⏳ Processing 🟢 Yes -
Phi-3-medium-128k-instruct.IQ2_XXS IQ2_XXS - ⏳ Processing 🟢 Yes -
Phi-3-medium-128k-instruct.IQ1_M IQ1_M - ⏳ Processing 🟢 Yes -
Phi-3-medium-128k-instruct.IQ1_S IQ1_S - ⏳ Processing 🟢 Yes -

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-medium-128k-instruct-IMat-GGUF --include "Phi-3-medium-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-medium-128k-instruct-IMat-GGUF --include "Phi-3-medium-128k-instruct.Q8_0/*" --local-dir Phi-3-medium-128k-instruct.Q8_0
# see FAQ for merging GGUF's

Inference

Simple chat template 

<|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-medium-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-medium-128k-instruct.Q8_0)
  3. Run gguf-split --merge Phi-3-medium-128k-instruct.Q8_0/Phi-3-medium-128k-instruct.Q8_0-00001-of-XXXXX.gguf Phi-3-medium-128k-instruct.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!