Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-F16.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-F32.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+embeddinggemma-300M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+base_model: 
+  - google/embeddinggemma-300m
+language:
+  - en
+model_creator: Google
+model_name: embeddinggemma-300m
+model_type: gemma-embedding
+quantized_by: s3dev-ai
+tags:
+  - sentence-similarity
+---
+
+# Overview
+
+This page provides various quantisations of the [base model](https://huggingface.co/google/embeddinggemma-300m), in GGUF format.
+- google/embeddinggemma-300m
+
+# Model Description
+
+For a full model description, please refer to the [base model's](https://huggingface.co/google/embeddinggemma-300m) card.
+
+## How are the GGUF files created?
+After cloning the author's original base model repository, `llama.cpp` is used to convert the model to a GGML compatible file, using `f32` as the output type; preserving the original fidelity. The model is converted *un-altered*, unless otherwise stated.
+
+Finally, for each respective quantisation level, `llama.cpp`'s `llama-quantize` executable is called using the F32 GGUF file as the source file.  
+
+## Quantisations
+
+To help visualise the difference in model quantisation (i.e. level of retained fidelity), the image below shows the cosine similarity scores for each quantisation, baselined against the 32-bit base model. It can be observed that lower fidelity yields a wider scatter in scores, relative to the 32-bit model.
+
+The underlying [base dataset](https://huggingface.co/datasets/sentence-transformers/stsb) was sampled to 1000 records with a unbiased similarity score distribution. Using the various quantisation levels of this model, embeddings were created for `sentence1` and `sentence2`. Finally, a cosine similarity score was calculated across the two embeddings, and plotted on the graph.   
+
+> [!NOTE] **Note:** This graph currently only features a single trend, which was created against the un-quantised 32-bit model. Although the quantised GGUF files are available, neither `sentence-transformers` nor `llama-cpp-python` have been updated to support the `gemma-embedding` format, so we can't use them (yet).
+>
+> As soon as support is available, we'll update this graph to display the fidelity for the quantisations. 
+
+<!-- Image alignment -->
+<div align="center">
+  <img src="imgs/embgemma.png" alt="Quantisation Levels" width="90%">
+</div>
+

embeddinggemma-300M-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bdbd8516756d819f2ac1c0b39b2ace8b2c30c25f10545d2891cfde8c31ba53
+size 612429792

embeddinggemma-300M-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a025bd8fd2720415446420ada454a5187dd5d96ab93201627c0a7924baa6f14d
+size 612429792

embeddinggemma-300M-F32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3125072128fc76d1c1d8d19f7b095c7e3bfbf00594dcf8a8bd3bcb334935d57
+size 1217982432

embeddinggemma-300M-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f71b5de27e76e0e290f8d0fb8a954f940b9797599d5aa97e39e00719e2d701b
+size 212209632

embeddinggemma-300M-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676216d6d8abbd717688905a77230a213f9db095793ee8c1afb1aa5bf11eb531
+size 236337120

embeddinggemma-300M-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f806ff63e12b5eb74d57146de00f41ac536f112a2d0615e645a99d5fc9acb6
+size 246732768

embeddinggemma-300M-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb77011e65793a6126ea6d317fc7ee31a20f4f5b59902fcc8a528e5fd57fa53
+size 260390880

embeddinggemma-300M-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6145ab14054cf8420e8e11cc4680455566a7e865600ece8e06d75adaaf39032a
+size 328576992

sha256/embeddinggemma-300M-BF16.sha256

@@ -0,0 +1 @@
+54bdbd8516756d819f2ac1c0b39b2ace8b2c30c25f10545d2891cfde8c31ba53  embeddinggemma-300M-BF16.gguf

sha256/embeddinggemma-300M-F16.sha256

@@ -0,0 +1 @@
+a025bd8fd2720415446420ada454a5187dd5d96ab93201627c0a7924baa6f14d  embeddinggemma-300M-F16.gguf

sha256/embeddinggemma-300M-F32.sha256

@@ -0,0 +1 @@
+a3125072128fc76d1c1d8d19f7b095c7e3bfbf00594dcf8a8bd3bcb334935d57  embeddinggemma-300M-F32.gguf

sha256/embeddinggemma-300M-Q2_K.sha256

@@ -0,0 +1 @@
+5f71b5de27e76e0e290f8d0fb8a954f940b9797599d5aa97e39e00719e2d701b  embeddinggemma-300M-Q2_K.gguf

sha256/embeddinggemma-300M-Q4_K_M.sha256

@@ -0,0 +1 @@
+676216d6d8abbd717688905a77230a213f9db095793ee8c1afb1aa5bf11eb531  embeddinggemma-300M-Q4_K_M.gguf

sha256/embeddinggemma-300M-Q5_K_M.sha256

@@ -0,0 +1 @@
+31f806ff63e12b5eb74d57146de00f41ac536f112a2d0615e645a99d5fc9acb6  embeddinggemma-300M-Q5_K_M.gguf

sha256/embeddinggemma-300M-Q6_K.sha256

@@ -0,0 +1 @@
+6cb77011e65793a6126ea6d317fc7ee31a20f4f5b59902fcc8a528e5fd57fa53  embeddinggemma-300M-Q6_K.gguf

sha256/embeddinggemma-300M-Q8_0.sha256

@@ -0,0 +1 @@
+6145ab14054cf8420e8e11cc4680455566a7e865600ece8e06d75adaaf39032a  embeddinggemma-300M-Q8_0.gguf