gemma-2-2b-IMat-GGUF

legraphista/gemma-2-2b-IMat-GGUF

gemma-2-2b-IMat-GGUF is a text generation model from legraphista. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as gemma.

Llama.cpp imatrix quantization of google/gemma-2-2b

Downloads · 30 days

1.6K

7% of all-time downloads

All-time downloads

23.7K

Public

Repo size

54 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf54 GB · 100%

At a glance

Task: Text Generation
Library: gguf
License: gemma
Access: Public
Created: Jul 31, 2024
Updated: Jul 31, 2024
SHA: 7e5046dd

Try a prompt

Base models

google/gemma-2-2b

Model card

From the Hugging Face model README

gemma-2-2b-IMat-GGUF

Llama.cpp imatrix quantization of google/gemma-2-2b

Original Model: google/gemma-2-2b
Original dtype: FP32 (float32)
Quantized by: llama.cpp b3496
IMatrix dataset: here

Files
Downloading using huggingface-cli
Inference
- 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

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
gemma-2-2b.Q8_0.gguf	Q8_0	2.78GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q6_K.gguf	Q6_K	2.15GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q4_K.gguf	Q4_K	1.71GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q3_K.gguf	Q3_K	1.46GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q2_K.gguf	Q2_K	1.23GB	✅ Available	🟢 IMatrix	📦 No

All Quants

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
gemma-2-2b.F32.gguf	F32	10.46GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.BF16.gguf	BF16	5.24GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.FP16.gguf	F16	5.24GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q8_0.gguf	Q8_0	2.78GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q6_K.gguf	Q6_K	2.15GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q5_K.gguf	Q5_K	1.92GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q5_K_S.gguf	Q5_K_S	1.88GB	✅ Available	⚪ Static	📦 No
gemma-2-2b.Q4_K.gguf	Q4_K	1.71GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q4_K_S.gguf	Q4_K_S	1.64GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ4_NL.gguf	IQ4_NL	1.63GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ4_XS.gguf	IQ4_XS	1.57GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q3_K.gguf	Q3_K	1.46GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q3_K_L.gguf	Q3_K_L	1.55GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q3_K_S.gguf	Q3_K_S	1.36GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ3_M.gguf	IQ3_M	1.39GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ3_S.gguf	IQ3_S	1.36GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ3_XS.gguf	IQ3_XS	1.31GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ3_XXS.gguf	IQ3_XXS	1.18GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q2_K.gguf	Q2_K	1.23GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.Q2_K_S.gguf	Q2_K_S	1.17GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ2_M.gguf	IQ2_M	1.09GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ2_S.gguf	IQ2_S	1.03GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ2_XS.gguf	IQ2_XS	1.00GB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ2_XXS.gguf	IQ2_XXS	943.19MB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ1_M.gguf	IQ1_M	873.80MB	✅ Available	🟢 IMatrix	📦 No
gemma-2-2b.IQ1_S.gguf	IQ1_S	832.16MB	✅ Available	🟢 IMatrix	📦 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/gemma-2-2b-IMat-GGUF --include "gemma-2-2b.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/gemma-2-2b-IMat-GGUF --include "gemma-2-2b.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Llama.cpp

llama.cpp/main -m gemma-2-2b.Q8_0.gguf --color -i -p "prompt here"

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?

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
Locate your GGUF chunks folder (ex: gemma-2-2b.Q8_0)
Run gguf-split --merge gemma-2-2b.Q8_0/gemma-2-2b.Q8_0-00001-of-XXXXX.gguf gemma-2-2b.Q8_0.gguf
- Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!

Task: Text Generation
Library: gguf
License: gemma
Created: Jul 31, 2024
Updated: Jul 31, 2024