Compatibility with llama.cpp commit 4524290e8

#1
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
  ---
16
 
17
  ***
18
- **Warning**: There is a llama.cpp PR [about to be merged](https://github.com/ggerganov/llama.cpp/pull/5500) that will break compatibility with these files. Keep an eye out for updates to this repo.
19
  ***
20
 
21
  <br/>
@@ -31,7 +31,7 @@ This repo contains llama.cpp-compatible files for [nomic-embed-text-v1](https://
31
 
32
  llama.cpp will default to 2048 tokens of context with these files. To use the full 8192 tokens that Nomic Embed is benchmarked on, you will have to choose a context extension method. The original model uses Dynamic NTK-Aware RoPE scaling, but that is not currently available in llama.cpp. A combination of YaRN and linear scaling is an acceptable substitute.
33
 
34
- These files were converted and quantized with llama.cpp commit [6c00a0669](https://github.com/ggerganov/llama.cpp/commit/6c00a066928b0475b865a2e3e709e2166e02d548).
35
 
36
  ## Example `llama.cpp` Command
37
 
@@ -56,7 +56,7 @@ Compute multiple embeddings:
56
 
57
  ## Compatibility
58
 
59
- These files are compatible with llama.cpp as commit [ea9c8e114](https://github.com/ggerganov/llama.cpp/commit/ea9c8e11436ad50719987fa23a289c74b7b40d40) from 2/13/2024.
60
 
61
 
62
  ## Provided Files
 
15
  ---
16
 
17
  ***
18
+ **Note**: For compatiblity with current llama.cpp, please download the files published on 2/15/2024. The files originally published here will fail to load.
19
  ***
20
 
21
  <br/>
 
31
 
32
  llama.cpp will default to 2048 tokens of context with these files. To use the full 8192 tokens that Nomic Embed is benchmarked on, you will have to choose a context extension method. The original model uses Dynamic NTK-Aware RoPE scaling, but that is not currently available in llama.cpp. A combination of YaRN and linear scaling is an acceptable substitute.
33
 
34
+ These files were converted and quantized with llama.cpp [PR 5500](https://github.com/ggerganov/llama.cpp/pull/5500), commit [34aa045de](https://github.com/ggerganov/llama.cpp/pull/5500/commits/34aa045de44271ff7ad42858c75739303b8dc6eb).
35
 
36
  ## Example `llama.cpp` Command
37
 
 
56
 
57
  ## Compatibility
58
 
59
+ These files are compatible with llama.cpp as of commit [4524290e8](https://github.com/ggerganov/llama.cpp/commit/4524290e87b8e107cc2b56e1251751546f4b9051) from 2/15/2024.
60
 
61
 
62
  ## Provided Files
nomic-embed-text-v1.Q2_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa3facae1fc208e8ea7c454663f7f2a8e35b1b475e95d06b0beed5cc09592f7f
3
  size 49361088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb87e81c67d34db721db27f093d1e87e4620001fe11e4566c5ceb88cd0fc667
3
  size 49361088
nomic-embed-text-v1.Q3_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea9a70eac0e6aa2a8688f413e16b8ee4ab843ab610eebcfb64fcdbf4928792bd
3
  size 71593088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1974d4dd71b76ae3a44b58c12bd753fd57f08975a81a77960097e285a01eb32
3
  size 71593088
nomic-embed-text-v1.Q3_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa11ac3d4b73f3b7f7dc9270645401700851c5c6a54fe467ecbfc53b97cf5b79
3
  size 67169408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5811832d7bf8cae9ec2824128e25a7b69bc752a7c993893df7ec80ff506424
3
  size 67169408
nomic-embed-text-v1.Q3_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f53883628b38585a2c9c326c3e9caf0229c53c719e8f3b2d6c1193c11fa7203
3
  size 59649152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c6e5a619c66d210da3058e4a36aeab1c49386fa4836cb165f2e81182875fde
3
  size 59649152
nomic-embed-text-v1.Q4_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e343400e108c888f42d6db5b182c724e8fc622c8f3098d65747664064d78685e
3
  size 77802880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca39592bb0191be78b0fa9263b96792203eaad7bd9de0d53ad7f07c1f7d59dc5
3
  size 77802880
nomic-embed-text-v1.Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:523e5a3a13d1bdc2ccec9a0fb37220f9538e88eef96c936881e42adb94b8497a
3
  size 84106624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b910918b82f87301b0301134c4a131a15a6123962e8b89a0554ba7357d285fb
3
  size 84106624
nomic-embed-text-v1.Q4_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1da11c80701340bc76ee1db073f8ab1567b4a2ae90c541db67a3994e3994c360
3
  size 78097792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b72dd549a1589e4047ed3cd737ba6ae974ae635a0e327f4352c56536573b9d4
3
  size 78097792
nomic-embed-text-v1.Q5_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ebde6badc9a620588a32d1dd1558ba4fe849220e1292832910e88bf599b1708
3
  size 94888768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3fac9da3c08434befcd3f4353e68df0f2b61dc200ee7b8a38afccf55e7fb0e7
3
  size 94888768
nomic-embed-text-v1.Q5_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:082ad550da44a065b91b7911606714bbcb25fca91d1b3f783883590ce1d78288
3
  size 99588928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b27adf775cc6976755da192c1982877c54c2cbbd2f47552b4189d96829657d0
3
  size 99588928
nomic-embed-text-v1.Q5_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afb65580df24d70bf4f52f1a8873ffe4ee27eba90859c3026d57f6ab0e62ebc2
3
  size 94888768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1590be631a94d824c148b2f1d4297c94edf35f538c17554ccc75ee44c377e5
3
  size 94888768
nomic-embed-text-v1.Q6_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:252457755ff74b7a33105aa67b9ca8dfa278fca52e792a8eff50d9563564dd86
3
  size 113042528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80b0668ea5ce20f55075cd46237944172b93f61907b47fa022fe35eaf05181d
3
  size 113042528
nomic-embed-text-v1.Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecbb94390c4ad47d9f79ee0bb717910dc5920c5eca107f60b75b2fe1656a1d8e
3
  size 146146432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194206fcf0e77681bd2eaa3517b6fce880e1a3e15ef89935a77a1892574d15f7
3
  size 146146432
nomic-embed-text-v1.f16.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ecf66c73efa2f9a78794ff7101c042a4943a663a236e1a08e7029e809b99599
3
  size 274290560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17ebde8d22d345aead60b0ed10726e8c45a06f4ba9a45223ab594526542e58f
3
  size 274290560
nomic-embed-text-v1.f32.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98617d300766fa4ee4172f06424ce8d0a95c6c051d274d57615f4d86f1aaa942
3
  size 547664768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1798c9e108b1d27fe3501339ac7785ea37f6504ee928ef7802ad881219e4c04c
3
  size 547664768