bartowski commited on
Commit
f68bdb6
·
verified ·
1 Parent(s): 9afe36d

Llamacpp quants

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ base_model: google/gemma-2-9b-it
16
 
17
  ## Llamacpp imatrix Quantizations of gemma-2-9b-it
18
 
19
- 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.
20
 
21
  Original model: https://huggingface.co/google/gemma-2-9b-it
22
 
@@ -25,9 +25,11 @@ All quants made using imatrix option with dataset from [here](https://gist.githu
25
  ## Prompt format
26
 
27
  ```
28
- <start_of_turn>user
29
  {prompt}<end_of_turn>
30
  <start_of_turn>model
 
 
31
 
32
  ```
33
 
 
16
 
17
  ## Llamacpp imatrix Quantizations of gemma-2-9b-it
18
 
19
+ 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.
20
 
21
  Original model: https://huggingface.co/google/gemma-2-9b-it
22
 
 
25
  ## Prompt format
26
 
27
  ```
28
+ <bos><start_of_turn>user
29
  {prompt}<end_of_turn>
30
  <start_of_turn>model
31
+ <end_of_turn>
32
+ <start_of_turn>model
33
 
34
  ```
35
 
gemma-2-9b-it-IQ2_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d15fdae729a79d5be3224dfc91ca1c3e36ca5c1b2b45f58d21a5b6ffd0b4f218
3
- size 3434669824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f1598b84ff74b057ebbc772ff921b74d8ec2bfc04a46b0e012ba3a55ac88d5
3
+ size 3434669920
gemma-2-9b-it-IQ2_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a8d6e35d9486aeb911874e0191d236989b219b2aff28624cd79f2fa1a0adada
3
- size 3211486976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee7ef22832856ad1767627530028b325d85c6b0818e5ae8bcdcd7c9099d4085
3
+ size 3211487072
gemma-2-9b-it-IQ2_XS.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:519b7c3c3dec688972028bbaa3d1ceeb57219d2401b40606817806b192234b88
3
- size 3067381504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1b7b3b9418dca6c7320c996fd309ff19b645b254cfd01d56dad45c3eda1191d
3
+ size 3067381600
gemma-2-9b-it-IQ3_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52887543e6b86c6c3b3e0809f93903d2c7c480ed75870b12fee2fd0f47c95747
3
- size 4494616320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264554168b51b3dbb416a994d4f4de761206e246f062dee7c5bfb75748eebcc5
3
+ size 4494616416
gemma-2-9b-it-IQ3_XS.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae768bece7b9a5fe4c6050ed56c5d18259ebbac3e469d72d339d7d6eccd570f5
3
- size 4144989952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e8cd37cf20ef4439b8ca807f7d9a694baeabe544855fc36c3cb2a929c867f6
3
+ size 4144990048
gemma-2-9b-it-IQ3_XXS.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01757277da17951371c892938f2f6a9962d95f478dff735a586d4e9fdb3f98f4
3
- size 3796739840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ae50cd71783cae22d80c1eed4578a12c0a33656b8a72454eb0aa7bac517d2c
3
+ size 3796739936
gemma-2-9b-it-IQ4_XS.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d245892642033bd773aa58de1c56e42665ece1f7f7c0ec44dcfe3a96b7d9651e
3
- size 5183031040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:717d862253259f2b9f8bae6dacfe2de4e548e07b681636abaccc5857cc64c539
3
+ size 5183031136
gemma-2-9b-it-Q2_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18a16f7a5aeec0b980b4de59b5e1360230ae1c8adfd134d1767c9e7e11d98e6e
3
- size 3805398784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbc9bbfc3177d7c755469f513a26957a65daf267f50eea6b9ecf0aaa01e9824
3
+ size 3805398880
gemma-2-9b-it-Q2_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:808f8acb636b47d4a4f3e98c1fff54a71eb6fce8a089f81c3fe2fe393fb78617
3
- size 4887766784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b449f7ab8849467305367a6b7954f1a7e38b1985d654c31074e5bf8138eb8978
3
+ size 4887766880
gemma-2-9b-it-Q3_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc77fafad18312c3f3d0d316e2edefd28dcd539cba10cc1fbe7f0dc3d53dae6d
3
- size 5132453632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdecc51155ec3257ad944b906fbdb6db956270796f8770a696fb4dd5360236c7
3
+ size 5132453728
gemma-2-9b-it-Q3_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ff6aebb809a52bf5560d23c4fda7e96ee9a3a75cf7ab0e20ab3089017020645
3
- size 4761782016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9336a60687e668641ce713f04bc294393ad67f73eb67cd26d62d2d33c1fbb4e1
3
+ size 4761782112
gemma-2-9b-it-Q3_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1866bcc45b83bebacef1cf9daf09bc94036a2705afbf8eaf9369f9bc6006209e
3
- size 4337665792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1dbe1bb26875cc2e2e5198c366dd87d1656475c0fe081da99af1d1fbb5ada3
3
+ size 4337665888
gemma-2-9b-it-Q3_K_XL.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3c84c98a66aae4b79d92903f1cab526a158315c26a2851cdb6a6174720300a7
3
- size 6214821632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89d15d86b6417353f2deefeafc9bc060f61d6a482c715f991e1be99d60f4148
3
+ size 6214821728
gemma-2-9b-it-Q4_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fee521f3b0f96aa358c0da9d5a8ac18d1ee81426059599ab7b15e9f06c3dc49
3
- size 6843426560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb3ad73320d4814c1935766f0b9eaf47de1f8672c6688080db2bfa400eab1ad
3
+ size 6843426656
gemma-2-9b-it-Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5375972196fae34c1a767bbeba93938d86abb39f2f91ea5453efa36ead6569f1
3
- size 5761058560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70fd20caec79fb953b83031c46ddea4e99905835a66af7b8a856aa1b2534614
3
+ size 5761058656
gemma-2-9b-it-Q4_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:225432bb66c374da3a94ed5d5c1ff0e6b80d742a8a09281a58e2fff8e9efa72e
3
- size 5478926080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c801ce6f8486ff5b6cdf958f2ecc75d0ba5a50626ac14d80a79d1434ef2e2ca
3
+ size 5478926176
gemma-2-9b-it-Q5_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:807d53fe895f460ccdb7817557965852a73886df2026c101457de9c7e3a038ad
3
- size 7729735424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ab83d6cc9e754af2c80bcf6009928c47d17813e7aa915d21062c4debfe8346
3
+ size 7729735520
gemma-2-9b-it-Q5_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f480cb36e05fedbae67e097840cd71999dde890d57287f4205a331a0d5cefe
3
- size 6647367424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78d0bd3513fedd4ba55adb4e97ca744b37f46d42aca11d97dd57dd506a2fd50
3
+ size 6647367520
gemma-2-9b-it-Q5_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:975f87d0482f74adedeadddeabb68d87b6202da0e7e237687215c6c69b43b91b
3
- size 6483592960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77eb98f95812f1af5fa004cc4d6a1e5e1a63668ec2d8b71af59ab2df97b0ba28
3
+ size 6483593056
gemma-2-9b-it-Q6_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edc2b9f3f811cb78101d618a2db360ca374584fbdb8540afae869a6fffaa6516
3
- size 7589070592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4ff889a8e5fb8a8844484a0a5d489a6352bf267c6f1e9e0e182ba5bc1970d7
3
+ size 7589070688
gemma-2-9b-it-Q6_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af575649b23922300468189a26e381951b298bdb18046f7aeb4fcc63bc30a5d6
3
- size 8671438592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864a9cade300574911946220d7db5fd1c37ab71101bbb4beedb6611a9cf23d61
3
+ size 8671438688
gemma-2-9b-it-Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f9a9de67bec3d6e8277c1964c278aa419c9ed7533cefe6595a8ee4e9c568d01
3
- size 9827149568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5ff18d06640d4f523cfcc2c699ac27165b0ce319d9894e7cd9771f77460c47
3
+ size 9827149664
gemma-2-9b-it-Q8_0_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61707731042388bfcf35eadbddfc0a812df783d41bf541de231ba5cda4775347
3
- size 10687309568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ac7f5be275544048dbbde28db798864c1371fbdba24cc83ebb4f4c45ca21d9
3
+ size 10687309664
gemma-2-9b-it-f32.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf05a8f90685a86b8b92c8de0b5777f3346a976f496123f36da8585c3177362
3
- size 36972881408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeab5ced5dd791e63b1bcee5823af35ce2fae0ca6438f0d788d4dd09b9d1fdc6
3
+ size 36972881504
gemma-2-9b-it.imatrix CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a2ec42f9516ace90f9ecb98781eef3db3b63040319ed9192ea3cf8782ebc454
3
  size 6116901
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e535b9f7be1305a997e288316242e42ccac1cf9810057c96bd6a194b3cc7495
3
  size 6116901