Llamacpp quants

README.md

@@ -9,12 +9,11 @@ extra_gated_prompt: >-
   Face and click below. Requests are processed immediately.
 extra_gated_button_content: Acknowledge license
 quantized_by: bartowski
-base_model: google/gemma-2-27b-it-GGUF
 ---
 
 ## Llamacpp imatrix Quantizations of gemma-2-27b-it
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3259">b3259</a> for quantization.
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3266">b3266</a> for quantization.
 
 Original model: https://huggingface.co/google/gemma-2-27b-it
 
@@ -23,9 +22,11 @@ All quants made using imatrix option with dataset from [here](https://gist.githu
 ## Prompt format
 
 ```
-<start_of_turn>user
+<bos><start_of_turn>user
 {prompt}<end_of_turn>
 <start_of_turn>model
+<end_of_turn>
+<start_of_turn>model
 
 ```
 

gemma-2-27b-it-IQ2_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac5e0423a14bd124310a9bbff4dfd2d0a6a8165162fd3c9f5090869a692d2e4
-size 9398878560
+oid sha256:b57a62bef93780a1f4443284c2560626e8cce03e8dc1093dc79e9a47ea8f0039
+size 9398878656

gemma-2-27b-it-IQ2_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8acc19032705252b5891883ef339107a4e7236da266307c3f2ff485414c45c
-size 8652161376
+oid sha256:eca060b0336b11a1d68416fc1c16e81af89a35e3fd88e3461cced97983cc1620
+size 8652161472

gemma-2-27b-it-IQ2_XS.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0667fdc5bc7635eb379f9cce9f3225719f87d3e062a4227be127f154d6843c00
-size 8399716704
+oid sha256:80bc7e22d276aa2ecf418e7d99d0410e276b79dc9f75f73e08374c6d14cde817
+size 8399716800

gemma-2-27b-it-IQ3_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56de27535c598d0419eb2e93502d8be65baac7b5cdfda610b8541cd2adf67dc
-size 12454830432
+oid sha256:62569c50d8b7b08c72f14e9f0ff6f0c688ec6f021a531a770d7e49f95ae6df0f
+size 12454830528

gemma-2-27b-it-IQ3_XS.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dfc33b9619f6c141a2b680fa5d625ce3f9b514b5e62b233ad5fd58985e056c8
-size 11550630240
+oid sha256:d33750cc8acae03b6849aff9478c703f62e4f140ba4c000b43fc04994ad62a93
+size 11550630336

gemma-2-27b-it-IQ3_XXS.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9dd8bcb4c6cec2c35bd1cdeaa295f6788ff8a7c656a2448b8f67db557fabc05
-size 10750755168
+oid sha256:382d5cd0ec92b8c0e10b27b3f63f761c7df894ef29e47272ada87a0bcf09d28d
+size 10750755264

gemma-2-27b-it-IQ4_XS.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136db68716327171facb0da75f5396e61175d99b953bdcbed8c1b228c366c85f
-size 14814421344
+oid sha256:ed2f0348cd1b2d445aab7b09e4d1d0810cde53b0ea9c323014c554c2f2ecf376
+size 14814421440

gemma-2-27b-it-Q2_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589b098ead37615a95d83181ce0f0d3a162b7bd720eae370029b5f452ef36612
-size 10449576288
+oid sha256:1196081ee282bed6de7af9c399bf976d263032f1ee871032f6ea41e737d88eb8
+size 10449576384

gemma-2-27b-it-Q2_K_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae47e19306cbc099f405720e84d65f5168cd1e315de886436bbd7e9b2fb00012
-size 11841192288
+oid sha256:ca3c39bd3ffb31a177bfe4d3a5e8eb7ef00d5b53c140a77e9f540105e9d4ab0a
+size 11841192384

gemma-2-27b-it-Q3_K_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef6c739293a83b428950abda322dbcd20893002b404f244f4c5881898e38a0bf
-size 14519361888
+oid sha256:668d77919a7b1ffe1dea3cf581a99e1a4946766e634faf854095ebcdd7f1f023
+size 14519361984

gemma-2-27b-it-Q3_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cc746e782593662436433a1541bd3dfcf3fc64b8ba9564361b2eeab5475937
-size 13424648544
+oid sha256:d84e63e1431f8bf0005d58e19dbf9931d89a8ca2250f12cd369f20485e80e2d2
+size 13424648640

gemma-2-27b-it-Q3_K_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe7885f7bdb3bf0bc8548c296f437fb576ed906043fd9f9c0c7ac84246d0972
-size 12169060704
+oid sha256:59b493539449b01fc2bdd6624267e4c119a02f1ff95e576ffdc28b24c019f96e
+size 12169060800

gemma-2-27b-it-Q3_K_XL.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042f847a41a3dfcf83414b203054ca044acab33d741114c864f15dd0c5539338
-size 15910977888
+oid sha256:c0bc9462a24c7fb5dbec57dd4d30d70083da04667ef287303b48d22bb62b579a
+size 15910977984

gemma-2-27b-it-Q4_K_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d35766b774effed0fb93535c2ec4a19a52a1ac263a865388ce8a1f4217297d
-size 18036998496
+oid sha256:6d3ffb19246c88d567e34a58d8e38ad828dac8d81faebc990f01c97d0ad0a5d0
+size 18036998592

gemma-2-27b-it-Q4_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6739763f1b7661d32bd63e05bc1131e5bb9dac436b249faf6c6edffa601c96
-size 16645382496
+oid sha256:ca86fbdb791842cf2e5eb276a6916e326b3b5d58d9ab60ee3e18b1c6f01fc181
+size 16645382592

gemma-2-27b-it-Q4_K_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4605b0667036d027a179e718a7182118d00db6242ca6f08d9e1ab0ba4afecd54
-size 15739265376
+oid sha256:0fd751dda128342f4296cb8388484f72e47de990cb8716c5f4b65589647a5f86
+size 15739265472

gemma-2-27b-it-Q5_K_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da959f7228be368760c7b0e55ae68b522582966b1d1b22ef4c6b2994a482ee18
-size 20799734112
+oid sha256:caa11566a6f2e91988308de687ab960991b76ba155e08a007e9051b134577913
+size 20799734208

gemma-2-27b-it-Q5_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c90d894225c760044fc37e0b0912c67268a7870fe01d445b1821b561ee0bab
-size 19408118112
+oid sha256:9048d3a9c292287d193af3f98a2898fc75b9168dea5680ba838fc048e3903015
+size 19408118208

gemma-2-27b-it-Q5_K_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0a3f5a02417eeb0e3a6bc45b0bce6b9b1f24d36afed1e8b1c93ff5d82f17a0
-size 18884206944
+oid sha256:6a04746410e8492f06ea2d1ab6ec0f30d5cbaf56027a1252191c2b9c2278e41d
+size 18884207040

gemma-2-27b-it-Q6_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460d88c4ad506163673fde237fef6be2c231a056926a40ef859ce32456c7a424
-size 22343524704
+oid sha256:33bdd099ee057c8097fa9a8a0e2d23807afea622b220376dc7b2aab8ea287917
+size 22343524800

gemma-2-27b-it-Q6_K_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f00d33b1feb33184d50cabf047cc9d53fb56ecb5f839e0cb8fbfba0f826a11
-size 23735140704
+oid sha256:ab32da8eed77f2368f76887b19d7fc87ae77247005d9ce02702979db8270da54
+size 23735140800

gemma-2-27b-it-Q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784146b99cc08e237292638d064150909a7e82cf6ecc55bed7d81328c58d42d2
-size 28937388384
+oid sha256:76f73556fa30bdfa510d3dacc5245d9488ca83e264c354512167a884a66746cd
+size 28937388480

gemma-2-27b-it-Q8_0_L.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f1c2a3807b2e8d56a705713a064fc03879da21564472fcdfc0477c0b65ba05
-size 30043308384
+oid sha256:d27e8b1954459960dcd4770644486dcfe815edc6f4b853427d3be7446023bf58
+size 30043308480

gemma-2-27b-it-f32.gguf/gemma-2-27b-it-f32-00001-of-00003.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40cffae24f3b2ef81b71f3f9395641e2d7b3b648c81ff6b37d16b496b655463b
-size 39605588416
+oid sha256:3de30298e3307ec26163cb5bf63c25c42e5924fd7167bbecbb7102408e5cd14c
+size 39605588480

gemma-2-27b-it.imatrix

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa62436bc9274e797e6a525815823c8c9f3baf1a011c4da34ee3252bc77cefd8
+oid sha256:de3960ddb965f3fbce726bac948f6f0bcf1e37a320b341fc19e383c6712bcf8b
 size 11786697