Cebtenzzre
commited on
Commit
•
1f34490
1
Parent(s):
84e6b93
Compatibility with llama.cpp commit 4524290e8 (#1)
Browse files- compatiblity with llama.cpp PR 5500 (f310e8bf48e70fee6eef9398af15c899cebd9505)
- update README (adb366a904fa60b2b775891fa339e35c09cf7daf)
- update README (4acf7e3ddebc39632034d13ada5fb0b17f6b9f35)
- update README (3c764bc6cda6c61f304362c3db155f890a6902a7)
- README.md +3 -3
- nomic-embed-text-v1.Q2_K.gguf +1 -1
- nomic-embed-text-v1.Q3_K_L.gguf +1 -1
- nomic-embed-text-v1.Q3_K_M.gguf +1 -1
- nomic-embed-text-v1.Q3_K_S.gguf +1 -1
- nomic-embed-text-v1.Q4_0.gguf +1 -1
- nomic-embed-text-v1.Q4_K_M.gguf +1 -1
- nomic-embed-text-v1.Q4_K_S.gguf +1 -1
- nomic-embed-text-v1.Q5_0.gguf +1 -1
- nomic-embed-text-v1.Q5_K_M.gguf +1 -1
- nomic-embed-text-v1.Q5_K_S.gguf +1 -1
- nomic-embed-text-v1.Q6_K.gguf +1 -1
- nomic-embed-text-v1.Q8_0.gguf +1 -1
- nomic-embed-text-v1.f16.gguf +1 -1
- nomic-embed-text-v1.f32.gguf +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ tags:
|
|
15 |
---
|
16 |
|
17 |
***
|
18 |
-
**
|
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 [
|
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 [
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
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:
|
3 |
size 547664768
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1798c9e108b1d27fe3501339ac7785ea37f6504ee928ef7802ad881219e4c04c
|
3 |
size 547664768
|