legraphista's picture
Upload README.md with huggingface_hub
e38399b verified
|
raw
history blame
5.08 kB
metadata
base_model: microsoft/Phi-3-medium-4k-instruct
inference: false
language:
  - multilingual
library_name: gguf
license: mit
license_link: https://huggingface.co./microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

Phi-3-medium-4k-instruct-IMat-GGUF

Llama.cpp imatrix quantization of microsoft/Phi-3-medium-4k-instruct

Original Model: microsoft/Phi-3-medium-4k-instruct
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b2998
IMatrix dataset: here

Files

IMatrix

Status: ⏳ Processing
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-medium-4k-instruct.Q8_0 Q8_0 - ⏳ Processing βšͺ No -
Phi-3-medium-4k-instruct.Q6_K.gguf Q6_K 11.45GB βœ… Available βšͺ No πŸ“¦ No
Phi-3-medium-4k-instruct.Q4_K Q4_K - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.Q3_K Q3_K - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.Q2_K Q2_K - ⏳ Processing 🟒 Yes -

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-medium-4k-instruct.FP16 F16 - ⏳ Processing βšͺ No -
Phi-3-medium-4k-instruct.BF16 BF16 - ⏳ Processing βšͺ No -
Phi-3-medium-4k-instruct.Q5_K Q5_K - ⏳ Processing βšͺ No -
Phi-3-medium-4k-instruct.Q5_K_S Q5_K_S - ⏳ Processing βšͺ No -
Phi-3-medium-4k-instruct.Q4_K_S Q4_K_S - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.Q3_K_L Q3_K_L - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.Q3_K_S Q3_K_S - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.Q2_K_S Q2_K_S - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ4_NL IQ4_NL - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ4_XS IQ4_XS - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ3_M IQ3_M - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ3_S IQ3_S - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ3_XS IQ3_XS - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ3_XXS IQ3_XXS - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ2_M IQ2_M - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ2_S IQ2_S - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ2_XS IQ2_XS - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ2_XXS IQ2_XXS - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ1_M IQ1_M - ⏳ Processing 🟒 Yes -
Phi-3-medium-4k-instruct.IQ1_S IQ1_S - ⏳ Processing 🟒 Yes -

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download legraphista/Phi-3-medium-4k-instruct-IMat-GGUF --include "Phi-3-medium-4k-instruct.Q8_0.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/Phi-3-medium-4k-instruct-IMat-GGUF --include "Phi-3-medium-4k-instruct.Q8_0/*" --local-dir Phi-3-medium-4k-instruct.Q8_0
# see FAQ for merging GGUF's

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-4k-instruct.Q8_0)
  3. Run gguf-split --merge Phi-3-medium-4k-instruct.Q8_0/Phi-3-medium-4k-instruct.Q8_0-00001-of-XXXXX.gguf Phi-3-medium-4k-instruct.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!