Llamacpp quants
Browse files- README.md +4 -3
- gemma-2-27b-it-IQ2_M.gguf +2 -2
- gemma-2-27b-it-IQ2_S.gguf +2 -2
- gemma-2-27b-it-IQ2_XS.gguf +2 -2
- gemma-2-27b-it-IQ3_M.gguf +2 -2
- gemma-2-27b-it-IQ3_XS.gguf +2 -2
- gemma-2-27b-it-IQ3_XXS.gguf +2 -2
- gemma-2-27b-it-IQ4_XS.gguf +2 -2
- gemma-2-27b-it-Q2_K.gguf +2 -2
- gemma-2-27b-it-Q2_K_L.gguf +2 -2
- gemma-2-27b-it-Q3_K_L.gguf +2 -2
- gemma-2-27b-it-Q3_K_M.gguf +2 -2
- gemma-2-27b-it-Q3_K_S.gguf +2 -2
- gemma-2-27b-it-Q3_K_XL.gguf +2 -2
- gemma-2-27b-it-Q4_K_L.gguf +2 -2
- gemma-2-27b-it-Q4_K_M.gguf +2 -2
- gemma-2-27b-it-Q4_K_S.gguf +2 -2
- gemma-2-27b-it-Q5_K_L.gguf +2 -2
- gemma-2-27b-it-Q5_K_M.gguf +2 -2
- gemma-2-27b-it-Q5_K_S.gguf +2 -2
- gemma-2-27b-it-Q6_K.gguf +2 -2
- gemma-2-27b-it-Q6_K_L.gguf +2 -2
- gemma-2-27b-it-Q8_0.gguf +2 -2
- gemma-2-27b-it-Q8_0_L.gguf +2 -2
- gemma-2-27b-it-f32.gguf/gemma-2-27b-it-f32-00001-of-00003.gguf +2 -2
- gemma-2-27b-it.imatrix +1 -1
README.md
CHANGED
@@ -9,12 +9,11 @@ extra_gated_prompt: >-
|
|
9 |
Face and click below. Requests are processed immediately.
|
10 |
extra_gated_button_content: Acknowledge license
|
11 |
quantized_by: bartowski
|
12 |
-
base_model: google/gemma-2-27b-it-GGUF
|
13 |
---
|
14 |
|
15 |
## Llamacpp imatrix Quantizations of gemma-2-27b-it
|
16 |
|
17 |
-
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/
|
18 |
|
19 |
Original model: https://huggingface.co/google/gemma-2-27b-it
|
20 |
|
@@ -23,9 +22,11 @@ All quants made using imatrix option with dataset from [here](https://gist.githu
|
|
23 |
## Prompt format
|
24 |
|
25 |
```
|
26 |
-
<start_of_turn>user
|
27 |
{prompt}<end_of_turn>
|
28 |
<start_of_turn>model
|
|
|
|
|
29 |
|
30 |
```
|
31 |
|
|
|
9 |
Face and click below. Requests are processed immediately.
|
10 |
extra_gated_button_content: Acknowledge license
|
11 |
quantized_by: bartowski
|
|
|
12 |
---
|
13 |
|
14 |
## Llamacpp imatrix Quantizations of gemma-2-27b-it
|
15 |
|
16 |
+
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.
|
17 |
|
18 |
Original model: https://huggingface.co/google/gemma-2-27b-it
|
19 |
|
|
|
22 |
## Prompt format
|
23 |
|
24 |
```
|
25 |
+
<bos><start_of_turn>user
|
26 |
{prompt}<end_of_turn>
|
27 |
<start_of_turn>model
|
28 |
+
<end_of_turn>
|
29 |
+
<start_of_turn>model
|
30 |
|
31 |
```
|
32 |
|
gemma-2-27b-it-IQ2_M.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b57a62bef93780a1f4443284c2560626e8cce03e8dc1093dc79e9a47ea8f0039
|
3 |
+
size 9398878656
|
gemma-2-27b-it-IQ2_S.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eca060b0336b11a1d68416fc1c16e81af89a35e3fd88e3461cced97983cc1620
|
3 |
+
size 8652161472
|
gemma-2-27b-it-IQ2_XS.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80bc7e22d276aa2ecf418e7d99d0410e276b79dc9f75f73e08374c6d14cde817
|
3 |
+
size 8399716800
|
gemma-2-27b-it-IQ3_M.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62569c50d8b7b08c72f14e9f0ff6f0c688ec6f021a531a770d7e49f95ae6df0f
|
3 |
+
size 12454830528
|
gemma-2-27b-it-IQ3_XS.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d33750cc8acae03b6849aff9478c703f62e4f140ba4c000b43fc04994ad62a93
|
3 |
+
size 11550630336
|
gemma-2-27b-it-IQ3_XXS.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:382d5cd0ec92b8c0e10b27b3f63f761c7df894ef29e47272ada87a0bcf09d28d
|
3 |
+
size 10750755264
|
gemma-2-27b-it-IQ4_XS.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed2f0348cd1b2d445aab7b09e4d1d0810cde53b0ea9c323014c554c2f2ecf376
|
3 |
+
size 14814421440
|
gemma-2-27b-it-Q2_K.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1196081ee282bed6de7af9c399bf976d263032f1ee871032f6ea41e737d88eb8
|
3 |
+
size 10449576384
|
gemma-2-27b-it-Q2_K_L.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3c39bd3ffb31a177bfe4d3a5e8eb7ef00d5b53c140a77e9f540105e9d4ab0a
|
3 |
+
size 11841192384
|
gemma-2-27b-it-Q3_K_L.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:668d77919a7b1ffe1dea3cf581a99e1a4946766e634faf854095ebcdd7f1f023
|
3 |
+
size 14519361984
|
gemma-2-27b-it-Q3_K_M.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d84e63e1431f8bf0005d58e19dbf9931d89a8ca2250f12cd369f20485e80e2d2
|
3 |
+
size 13424648640
|
gemma-2-27b-it-Q3_K_S.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59b493539449b01fc2bdd6624267e4c119a02f1ff95e576ffdc28b24c019f96e
|
3 |
+
size 12169060800
|
gemma-2-27b-it-Q3_K_XL.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0bc9462a24c7fb5dbec57dd4d30d70083da04667ef287303b48d22bb62b579a
|
3 |
+
size 15910977984
|
gemma-2-27b-it-Q4_K_L.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d3ffb19246c88d567e34a58d8e38ad828dac8d81faebc990f01c97d0ad0a5d0
|
3 |
+
size 18036998592
|
gemma-2-27b-it-Q4_K_M.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca86fbdb791842cf2e5eb276a6916e326b3b5d58d9ab60ee3e18b1c6f01fc181
|
3 |
+
size 16645382592
|
gemma-2-27b-it-Q4_K_S.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fd751dda128342f4296cb8388484f72e47de990cb8716c5f4b65589647a5f86
|
3 |
+
size 15739265472
|
gemma-2-27b-it-Q5_K_L.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa11566a6f2e91988308de687ab960991b76ba155e08a007e9051b134577913
|
3 |
+
size 20799734208
|
gemma-2-27b-it-Q5_K_M.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9048d3a9c292287d193af3f98a2898fc75b9168dea5680ba838fc048e3903015
|
3 |
+
size 19408118208
|
gemma-2-27b-it-Q5_K_S.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a04746410e8492f06ea2d1ab6ec0f30d5cbaf56027a1252191c2b9c2278e41d
|
3 |
+
size 18884207040
|
gemma-2-27b-it-Q6_K.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33bdd099ee057c8097fa9a8a0e2d23807afea622b220376dc7b2aab8ea287917
|
3 |
+
size 22343524800
|
gemma-2-27b-it-Q6_K_L.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab32da8eed77f2368f76887b19d7fc87ae77247005d9ce02702979db8270da54
|
3 |
+
size 23735140800
|
gemma-2-27b-it-Q8_0.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f73556fa30bdfa510d3dacc5245d9488ca83e264c354512167a884a66746cd
|
3 |
+
size 28937388480
|
gemma-2-27b-it-Q8_0_L.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d27e8b1954459960dcd4770644486dcfe815edc6f4b853427d3be7446023bf58
|
3 |
+
size 30043308480
|
gemma-2-27b-it-f32.gguf/gemma-2-27b-it-f32-00001-of-00003.gguf
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3de30298e3307ec26163cb5bf63c25c42e5924fd7167bbecbb7102408e5cd14c
|
3 |
+
size 39605588480
|
gemma-2-27b-it.imatrix
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 11786697
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3960ddb965f3fbce726bac948f6f0bcf1e37a320b341fc19e383c6712bcf8b
|
3 |
size 11786697
|