Hugging Face's logo

bartowski
/
Cerebrum-1.0-8x7b-GGUF-old

Text Generation
GGUF
Model card Files Community
1
bartowski commited on
Commit
d6424a9
•
1 Parent(s): 2d8220c

Llamacpp quants

Browse files
Files changed (22) hide show
  1. .gitattributes +19 -0
  2. Cerebrum-1.0-8x7b-IQ3_M.gguf +3 -0
  3. Cerebrum-1.0-8x7b-IQ3_S.gguf +3 -0
  4. Cerebrum-1.0-8x7b-IQ4_NL.gguf +3 -0
  5. Cerebrum-1.0-8x7b-IQ4_XS.gguf +3 -0
  6. Cerebrum-1.0-8x7b-Q2_K.gguf +3 -0
  7. Cerebrum-1.0-8x7b-Q3_K_L.gguf +3 -0
  8. Cerebrum-1.0-8x7b-Q3_K_M.gguf +3 -0
  9. Cerebrum-1.0-8x7b-Q3_K_S.gguf +3 -0
  10. Cerebrum-1.0-8x7b-Q4_0.gguf +3 -0
  11. Cerebrum-1.0-8x7b-Q4_K_M.gguf +3 -0
  12. Cerebrum-1.0-8x7b-Q4_K_S.gguf +3 -0
  13. Cerebrum-1.0-8x7b-Q5_0.gguf +3 -0
  14. Cerebrum-1.0-8x7b-Q5_K_M.gguf +3 -0
  15. Cerebrum-1.0-8x7b-Q5_K_S.gguf +3 -0
  16. Cerebrum-1.0-8x7b-Q6_K.gguf +3 -0
  17. Cerebrum-1.0-8x7b-Q8_0.gguf +3 -0
  18. Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_a +3 -0
  19. Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_b +3 -0
  20. Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_c +3 -0
  21. Cerebrum-1.0-8x7b-fp16.gguf/combine.sh +2 -0
  22. README.md +35 -0
.gitattributes CHANGED
@@ -33,3 +33,22 @@ 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
+ Cerebrum-1.0-8x7b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Cerebrum-1.0-8x7b-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Cerebrum-1.0-8x7b-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Cerebrum-1.0-8x7b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Cerebrum-1.0-8x7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Cerebrum-1.0-8x7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Cerebrum-1.0-8x7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Cerebrum-1.0-8x7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Cerebrum-1.0-8x7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Cerebrum-1.0-8x7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Cerebrum-1.0-8x7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Cerebrum-1.0-8x7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Cerebrum-1.0-8x7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Cerebrum-1.0-8x7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Cerebrum-1.0-8x7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Cerebrum-1.0-8x7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_a filter=lfs diff=lfs merge=lfs -text
53
+ Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_b filter=lfs diff=lfs merge=lfs -text
54
+ Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_c filter=lfs diff=lfs merge=lfs -text
Cerebrum-1.0-8x7b-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf20ed5e8605609c955c583f2f478fdaee51a1b8ab461e798d12d435310b7ad
3
+ size 21428709856
Cerebrum-1.0-8x7b-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43790c6523778facb8c001de060f828105bcd4574b6546adc942c49dcde1723d
3
+ size 20430465504
Cerebrum-1.0-8x7b-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f2b4d7bc8830552628db0ed1040408a761a8ef879fae5887527d8ec7fa540c
3
+ size 26743523808
Cerebrum-1.0-8x7b-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:598244cad949da46c385fe907fbd7e09403825d3ae9607016839cdc57fe97d43
3
+ size 25372084704
Cerebrum-1.0-8x7b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e25e5553336a1cba210d641cf8eec1d3fc342ae8bb68e2cbbef95a1a4928e47
3
+ size 17309174240
Cerebrum-1.0-8x7b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803331743dd11b3783d92b981a62082a815063dd39e4a9629548e7b71baf2c68
3
+ size 24167590368
Cerebrum-1.0-8x7b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75a888ae9cbd44b7a58b2985d02c8284d95f4b7dd6879e1d99dbfdaf81dc083
3
+ size 22544394720
Cerebrum-1.0-8x7b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209030762c71e40310ec37156d74fc84187310dc97dccc92a0383b2cd69094ce
3
+ size 20430465504
Cerebrum-1.0-8x7b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6764161ec6b96d768c0e2dace92e0c63573094189231746e7f5e92ffbce1af2d
3
+ size 26441533920
Cerebrum-1.0-8x7b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe5c45bcfba1808394f3079653ba55781dd92256a4b8f97248c3f80239aad32
3
+ size 28446411232
Cerebrum-1.0-8x7b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699c1b2491c2b81413de67a628a38eed86eb61ecfddd53209d4fa9d28f118ce4
3
+ size 26743523808
Cerebrum-1.0-8x7b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724483c380214a5ae8d3614a93fe11ea9b5caba788b832ab8e3e9b88ba4697e3
3
+ size 32229280224
Cerebrum-1.0-8x7b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa46596faaabe5132db7e2360913cfaee01784b9d9a80552e1d6177f3f47d7e1
3
+ size 33227524576
Cerebrum-1.0-8x7b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a03f766fa31a8eb258b6b73e58dbe6c42ffeedc3e5afd56418d47d966d0673
3
+ size 32229280224
Cerebrum-1.0-8x7b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364532e3dbabd582de8376a6bf7c1ba9532769d76dd401ea57e070d5cf7806b5
3
+ size 38378760672
Cerebrum-1.0-8x7b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0523c46c27cc3e48660e5187b964e8510b5ae9268822c93b347ca86fe198cf31
3
+ size 49624263136
Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_a ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a718486adc9d08c4161f8dfe3c93ffefd52eb61c51d57938f2f5d3cd1939452a
3
+ size 31135632865
Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c52369d61adef76070b7bc5c38a6e5f6b90d77bf5065e8b8a31e33447f6f34e
3
+ size 31135632865
Cerebrum-1.0-8x7b-fp16.gguf/Cerebrum-1.0-8x7b-fp16_part_c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc575e7619b9472bf8aaf3622871fcd7d065565fc063a1f739767bd04bcfa7e
3
+ size 31135632862
Cerebrum-1.0-8x7b-fp16.gguf/combine.sh ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ #!/bin/bash
2
+ cat Cerebrum-1.0-8x7b-fp16_part_* > "Cerebrum-1.0-8x7b-fp16.gguf"
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
3
+ license: apache-2.0
4
+ quantized_by: bartowski
5
+ pipeline_tag: text-generation
6
+ ---
7
+
8
+ ## Llamacpp Quantizations of Cerebrum-1.0-8x7b
9
+
10
+ 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.
11
+
12
+ Original model: https://huggingface.co/AetherResearch/Cerebrum-1.0-8x7b
13
+
14
+ Download a file (not the whole branch) from below:
15
+
16
+ | Filename | Quant type | File Size | Description |
17
+ | -------- | ---------- | --------- | ----------- |
18
+ | [Cerebrum-1.0-8x7b-Q8_0.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q8_0.gguf) | Q8_0 | 49.62GB | Extremely high quality, generally unneeded but max available quant. |
19
+ | [Cerebrum-1.0-8x7b-Q6_K.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q6_K.gguf) | Q6_K | 38.37GB | Very high quality, near perfect, *recommended*. |
20
+ | [Cerebrum-1.0-8x7b-Q5_K_M.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q5_K_M.gguf) | Q5_K_M | 33.22GB | High quality, very usable. |
21
+ | [Cerebrum-1.0-8x7b-Q5_K_S.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q5_K_S.gguf) | Q5_K_S | 32.22GB | High quality, very usable. |
22
+ | [Cerebrum-1.0-8x7b-Q5_0.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q5_0.gguf) | Q5_0 | 32.22GB | High quality, older format, generally not recommended. |
23
+ | [Cerebrum-1.0-8x7b-Q4_K_M.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q4_K_M.gguf) | Q4_K_M | 28.44GB | Good quality, similar to 4.25 bpw. |
24
+ | [Cerebrum-1.0-8x7b-Q4_K_S.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q4_K_S.gguf) | Q4_K_S | 26.74GB | Slightly lower quality with small space savings. |
25
+ | [Cerebrum-1.0-8x7b-IQ4_NL.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-IQ4_NL.gguf) | IQ4_NL | 26.74GB | Good quality, similar to Q4_K_S, new method of quanting, |
26
+ | [Cerebrum-1.0-8x7b-IQ4_XS.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-IQ4_XS.gguf) | IQ4_XS | 25.37GB | Decent quality, new method with similar performance to Q4. |
27
+ | [Cerebrum-1.0-8x7b-Q4_0.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q4_0.gguf) | Q4_0 | 26.44GB | Decent quality, older format, generally not recommended. |
28
+ | [Cerebrum-1.0-8x7b-IQ3_M.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-IQ3_M.gguf) | IQ3_M | 21.42GB | Medium-low quality, new method with decent performance. |
29
+ | [Cerebrum-1.0-8x7b-IQ3_S.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-IQ3_S.gguf) | IQ3_S | 20.43GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
30
+ | [Cerebrum-1.0-8x7b-Q3_K_L.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q3_K_L.gguf) | Q3_K_L | 24.16GB | Lower quality but usable, good for low RAM availability. |
31
+ | [Cerebrum-1.0-8x7b-Q3_K_M.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q3_K_M.gguf) | Q3_K_M | 22.54GB | Even lower quality. |
32
+ | [Cerebrum-1.0-8x7b-Q3_K_S.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q3_K_S.gguf) | Q3_K_S | 20.43GB | Low quality, not recommended. |
33
+ | [Cerebrum-1.0-8x7b-Q2_K.gguf](https://huggingface.co/bartowski/Cerebrum-1.0-8x7b-GGUF/blob/main/Cerebrum-1.0-8x7b-Q2_K.gguf) | Q2_K | 17.30GB | Extremely low quality, *not* recommended.
34
+
35
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski