Hugging Face's logo

tensorblock
/
NeuralPipe-9B-merged-GGUF

GGUF
Merge
mergekit
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
a129d30
·
verified ·
1 Parent(s): 0eec39e

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. NeuralPipe-9B-merged-Q2_K.gguf +2 -2
  2. NeuralPipe-9B-merged-Q3_K_L.gguf +2 -2
  3. NeuralPipe-9B-merged-Q3_K_M.gguf +2 -2
  4. NeuralPipe-9B-merged-Q3_K_S.gguf +2 -2
  5. NeuralPipe-9B-merged-Q4_0.gguf +2 -2
  6. NeuralPipe-9B-merged-Q4_K_M.gguf +2 -2
  7. NeuralPipe-9B-merged-Q4_K_S.gguf +2 -2
  8. NeuralPipe-9B-merged-Q5_0.gguf +2 -2
  9. NeuralPipe-9B-merged-Q5_K_M.gguf +2 -2
  10. NeuralPipe-9B-merged-Q5_K_S.gguf +2 -2
  11. NeuralPipe-9B-merged-Q6_K.gguf +2 -2
  12. NeuralPipe-9B-merged-Q8_0.gguf +2 -2
  13. README.md +8 -4
NeuralPipe-9B-merged-Q2_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab76da2255ef23778c05f73ee8ea6a1e4f49b8196f4454259a72ac49b22e137
3
- size 3361244000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21e82af59fba27881cba91ba217627ad812c4199aadeeea58e07ac22c8102c9
3
+ size 3361244256
NeuralPipe-9B-merged-Q3_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7c76f8fde05be62f0a819bcd36b8e1aded29a5dab90d6f8aba416107cea9042
3
- size 4736394080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05640afed57cf7dd562c0f950eafdc95b8103c87417ce5502edeba61c4fc0dc6
3
+ size 4736394336
NeuralPipe-9B-merged-Q3_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7b9236796f6acf019e68345552951ff48440457aaa515a4ded14b8400215f7f
3
- size 4353663840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df7d303dd2c355b6c57f75a3cf68a81cd884da70c5f6002a75ae6ef0ef18e24
3
+ size 4353664096
NeuralPipe-9B-merged-Q3_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fb3ea89e21d228fc1cb50f9f898b26c67567f96b16b31951acb914c12cf74dc
3
- size 3914572640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65cb9ef3f47cfb64e0a4dd1c970cbefc7a80dba5cc60d62b173b525a58017643
3
+ size 3914572896
NeuralPipe-9B-merged-Q4_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97d3a3f8cac68584a3e50ff807c4194c34d1e595e5c39751033c27b1a7719811
3
- size 5090657120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75091c17b8462e9beb4a75b14af143de1d2bb18a337542a427a082714046e11
3
+ size 5090657376
NeuralPipe-9B-merged-Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6a78bfd693268328b2ce6e529f1a7f49be69500c1b10a6a9653529c3aa13433
3
- size 5415060320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e699755d05d96c6cd0da222953dbba08152f0e7b128ccab7f5b7839357fd50
3
+ size 5415060576
NeuralPipe-9B-merged-Q4_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:771ce500b27935390a3b9795a29746c6ce7efd81d09f52407f8ee2e8fb812682
3
- size 5129454432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e1d34b406b72c6e2bf4bf8dc5e76321f5161fa1e549071529be485737497ab
3
+ size 5129454688
NeuralPipe-9B-merged-Q5_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ee5e14f84aa6dc69bf1fc35afb72d007084935f6bbd56e8dae53569b5501e86
3
- size 6197560160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807351fe514e7a960d12a17577cb415d3a6a2abb8906c2d4981f30e136382b7f
3
+ size 6197560416
NeuralPipe-9B-merged-Q5_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c57d8d5bf72786424319ca5f5936ff1bc9361f7b00aa55fbc5b0f7aeb0a5198
3
- size 6364676960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d5f70a4444e0dd8f38bf1466f685cc11c44bf183ac1c11210a2ba336bae5cc
3
+ size 6364677216
NeuralPipe-9B-merged-Q5_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd159fd5ffd80dd3214d5602c448faa4cdd504d8c8e254f40b8dc2cd2ef9d60
3
- size 6197560160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8305fd6ea1074a37aaf88d0026d3882056422d8a45c5f5e1f2c2405cff461ab0
3
+ size 6197560416
NeuralPipe-9B-merged-Q6_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:872f7a9467c89fcbc5a620af523beb63e3290cfd8733148101e4a4d3be9ddbea
3
- size 7373644640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2992612c21261eeaf5d2d8600705bf205126604d4e044d6a7dba9578d56edbfd
3
+ size 7373644896
NeuralPipe-9B-merged-Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bb7227bee62a14a067942b05bdc2f9bbf4ed376288698962af16dd4f50a32b6
3
- size 9550015264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a9936155b717a5239774c4f35369841ce42c7fbf05290698212a5ab180e7ba
3
+ size 9550015520
README.md CHANGED
@@ -5,7 +5,7 @@ tags:
5
  - mergekit
6
  - TensorBlock
7
  - GGUF
8
- base_model: shadowml/NeuralPipe-9B-merged
9
  ---
10
 
11
  <div style="width: auto; margin-left: auto; margin-right: auto">
@@ -19,9 +19,9 @@ base_model: shadowml/NeuralPipe-9B-merged
19
  </div>
20
  </div>
21
 
22
- ## shadowml/NeuralPipe-9B-merged - GGUF
23
 
24
- This repo contains GGUF format model files for [shadowml/NeuralPipe-9B-merged](https://huggingface.co/shadowml/NeuralPipe-9B-merged).
25
 
26
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
27
 
@@ -34,7 +34,11 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
34
  ## Prompt template
35
 
36
  ```
37
-
 
 
 
 
38
  ```
39
 
40
  ## Model file specification
 
5
  - mergekit
6
  - TensorBlock
7
  - GGUF
8
+ base_model: mlabonne/NeuralPipe-9B-merged
9
  ---
10
 
11
  <div style="width: auto; margin-left: auto; margin-right: auto">
 
19
  </div>
20
  </div>
21
 
22
+ ## mlabonne/NeuralPipe-9B-merged - GGUF
23
 
24
+ This repo contains GGUF format model files for [mlabonne/NeuralPipe-9B-merged](https://huggingface.co/mlabonne/NeuralPipe-9B-merged).
25
 
26
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
27
 
 
34
  ## Prompt template
35
 
36
  ```
37
+ <|im_start|>system
38
+ {system_prompt}<|im_end|>
39
+ <|im_start|>user
40
+ {prompt}<|im_end|>
41
+ <|im_start|>assistant
42
  ```
43
 
44
  ## Model file specification