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

huggingface.co
Total runs: 562
24-hour runs: 0
7-day runs: 108
30-day runs: 358
Model's Last Updated: May 27 2024
text-generation

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

Model Details of Phi-3-medium-4k-instruct-IMat-GGUF

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: โœ… Available
Link: here

Common Quants
Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-medium-4k-instruct.Q8_0.gguf Q8_0 14.83GB โœ… Available โšช No ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q6_K.gguf Q6_K 11.45GB โœ… Available โšช No ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q4_K.gguf Q4_K 8.57GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q3_K.gguf Q3_K 6.92GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q2_K.gguf Q2_K 5.14GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
All Quants
Filename Quant type File Size Status Uses IMatrix Is Split
Phi-3-medium-4k-instruct.FP16.gguf F16 27.92GB โœ… Available โšช No ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.BF16.gguf BF16 27.92GB โœ… Available โšช No ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q5_K.gguf Q5_K 10.07GB โœ… Available โšช No ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q5_K_S.gguf Q5_K_S 9.62GB โœ… Available โšช No ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q4_K_S.gguf Q4_K_S 7.95GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q3_K_L.gguf Q3_K_L 7.49GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q3_K_S.gguf Q3_K_S 6.06GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.Q2_K_S.gguf Q2_K_S 4.77GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ4_NL.gguf IQ4_NL 7.90GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ4_XS.gguf IQ4_XS 7.47GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ3_M.gguf IQ3_M 6.47GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ3_S.gguf IQ3_S 6.06GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ3_XS.gguf IQ3_XS 5.81GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ3_XXS.gguf IQ3_XXS 5.45GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ2_M.gguf IQ2_M 4.72GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ2_S.gguf IQ2_S 4.34GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ2_XS.gguf IQ2_XS 4.13GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ2_XXS.gguf IQ2_XXS 3.72GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ1_M.gguf IQ1_M 3.24GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
Phi-3-medium-4k-instruct.IQ1_S.gguf IQ1_S 2.96GB โœ… Available ๐ŸŸข Yes ๐Ÿ“ฆ No
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

Inference
Simple chat template
<s><|user|>
I am going to Paris, what should I see?<|end|>
<|assistant|>
Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:

1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.
2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.
3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.

These are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|>
<|user|>
What is so great about #1?<|end|>
<|assistant|>
Llama.cpp
llama.cpp/main -m Phi-3-medium-4k-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-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 !

Runs of legraphista Phi-3-medium-4k-instruct-IMat-GGUF on huggingface.co

562
Total runs
0
24-hour runs
0
3-day runs
108
7-day runs
358
30-day runs

More Information About Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co Model

More Phi-3-medium-4k-instruct-IMat-GGUF license Visit here:

https://choosealicense.com/licenses/mit

Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co

Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co is an AI model on huggingface.co that provides Phi-3-medium-4k-instruct-IMat-GGUF's model effect (), which can be used instantly with this legraphista Phi-3-medium-4k-instruct-IMat-GGUF model. huggingface.co supports a free trial of the Phi-3-medium-4k-instruct-IMat-GGUF model, and also provides paid use of the Phi-3-medium-4k-instruct-IMat-GGUF. Support call Phi-3-medium-4k-instruct-IMat-GGUF model through api, including Node.js, Python, http.

Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co Url

https://huggingface.co/legraphista/Phi-3-medium-4k-instruct-IMat-GGUF

legraphista Phi-3-medium-4k-instruct-IMat-GGUF online free

Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co is an online trial and call api platform, which integrates Phi-3-medium-4k-instruct-IMat-GGUF's modeling effects, including api services, and provides a free online trial of Phi-3-medium-4k-instruct-IMat-GGUF, you can try Phi-3-medium-4k-instruct-IMat-GGUF online for free by clicking the link below.

legraphista Phi-3-medium-4k-instruct-IMat-GGUF online free url in huggingface.co:

https://huggingface.co/legraphista/Phi-3-medium-4k-instruct-IMat-GGUF

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

Phi-3-medium-4k-instruct-IMat-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Phi-3-medium-4k-instruct-IMat-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Phi-3-medium-4k-instruct-IMat-GGUF install, users can directly use Phi-3-medium-4k-instruct-IMat-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Phi-3-medium-4k-instruct-IMat-GGUF install url in huggingface.co:

https://huggingface.co/legraphista/Phi-3-medium-4k-instruct-IMat-GGUF

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

Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co Url

Provider of Phi-3-medium-4k-instruct-IMat-GGUF huggingface.co

legraphista
ORGANIZATIONS

Other API from legraphista