Hugging Face's logo

bartowski
/
Maverick-Math-7B-GGUF

Text Generation
GGUF
Model card Files
xet
Community
bartowski commited on
Commit
cd090aa
·
verified ·
1 Parent(s): 8b6aa56

Llamacpp quants

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. Maverick-Math-7B-Q2_K.gguf +3 -0
  3. Maverick-Math-7B-Q3_K_L.gguf +3 -0
  4. Maverick-Math-7B-Q3_K_M.gguf +3 -0
  5. Maverick-Math-7B-Q3_K_S.gguf +3 -0
  6. Maverick-Math-7B-Q4_0.gguf +3 -0
  7. Maverick-Math-7B-Q4_K_M.gguf +3 -0
  8. Maverick-Math-7B-Q4_K_S.gguf +3 -0
  9. Maverick-Math-7B-Q5_0.gguf +3 -0
  10. Maverick-Math-7B-Q5_K_M.gguf +3 -0
  11. Maverick-Math-7B-Q5_K_S.gguf +3 -0
  12. Maverick-Math-7B-Q6_K.gguf +3 -0
  13. Maverick-Math-7B-Q8_0.gguf +3 -0
  14. README.md +32 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Maverick-Math-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Maverick-Math-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Maverick-Math-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Maverick-Math-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Maverick-Math-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Maverick-Math-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Maverick-Math-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Maverick-Math-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Maverick-Math-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Maverick-Math-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Maverick-Math-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Maverick-Math-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Maverick-Math-7B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05a2eea013ca017f3df8b817f47dcabb13787fd69864ac1f7a81562bbd0db1b
3
+ size 2719241920
Maverick-Math-7B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff733396558b8a881d379756b7457cbe420b313947702cd1385e6bec0ec8a005
3
+ size 3822024384
Maverick-Math-7B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a04fc492b2b4e07a4b7b9f022b236d27b6a4ed6ce8a3f7280ca92c58b4fae8
3
+ size 3518985920
Maverick-Math-7B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d67c04523071e6e47d0f5cfeb53e705fcd9ff61ae9f97117280343ad762181
3
+ size 3164567232
Maverick-Math-7B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0cf5b93e1e46b56d35f7fc8ead15a4dfb3d00f48e6ea884c397a3eae6d0ccdb
3
+ size 4108916416
Maverick-Math-7B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0dc50666ddfb4234b14953742ade6704e1d0e718b28790e0a4b4b16509ec33
3
+ size 4368438976
Maverick-Math-7B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8dce7e81597b09aa3b1eac0d01d6996c802ef087c7bc78ab38fb62d1a73f59
3
+ size 4140373696
Maverick-Math-7B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56a3c41d3c105d43ae8d0b6764f9bd8a6b340e61befb32c0f6b7e976fe51ff2
3
+ size 4997715648
Maverick-Math-7B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c7da7b57be552e5d884dcb7e48965fd1c44f68fe75ba4ae20b76a6427fea8e
3
+ size 5131409088
Maverick-Math-7B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d304725ccebfefffc7db55e0181d0ddee41acf0eda5b1664947f5ea3ff0ced
3
+ size 4997715648
Maverick-Math-7B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2f20cd80ebfdae3a71f906fe6043e963c964662074701b76ebc3f220903eb1
3
+ size 5942064832
Maverick-Math-7B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3408567714a80b1e269dd7c87c8409db9eaa96939344a82661cbd3d7d4e451f2
3
+ size 7695857344
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - microsoft/orca-math-word-problems-200k
4
+ license: apache-2.0
5
+ quantized_by: bartowski
6
+ pipeline_tag: text-generation
7
+ ---
8
+
9
+ ## Llamacpp Quantizations of Maverick-Math-7B
10
+
11
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
12
+
13
+ Original model: https://huggingface.co/feeltheAGI/Maverick-Math-7B
14
+
15
+ Download a file (not the whole branch) from below:
16
+
17
+ | Filename | Quant type | File Size | Description |
18
+ | -------- | ---------- | --------- | ----------- |
19
+ | [Maverick-Math-7B-Q8_0.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
20
+ | [Maverick-Math-7B-Q6_K.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
21
+ | [Maverick-Math-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
22
+ | [Maverick-Math-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
23
+ | [Maverick-Math-7B-Q5_0.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
24
+ | [Maverick-Math-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
25
+ | [Maverick-Math-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
26
+ | [Maverick-Math-7B-Q4_0.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
27
+ | [Maverick-Math-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
28
+ | [Maverick-Math-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
29
+ | [Maverick-Math-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
30
+ | [Maverick-Math-7B-Q2_K.gguf](https://huggingface.co/bartowski/Maverick-Math-7B-GGUF/blob/main/Maverick-Math-7B-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
31
+
32
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski