Hugging Face's logo

bartowski
/
Beyonder-4x7B-v3-GGUF

Text Generation
GGUF
Mixture of Experts
frankenmoe
Merge
mergekit
lazymergekit
Inference Endpoints
conversational
Model card Files Community
bartowski commited on
Commit
ad8b7e4
·
verified ·
1 Parent(s): 0c97651

Llamacpp quants

Browse files
Files changed (18) hide show
  1. .gitattributes +16 -0
  2. Beyonder-4x7B-v3-IQ3_M.gguf +3 -0
  3. Beyonder-4x7B-v3-IQ3_S.gguf +3 -0
  4. Beyonder-4x7B-v3-IQ4_NL.gguf +3 -0
  5. Beyonder-4x7B-v3-IQ4_XS.gguf +3 -0
  6. Beyonder-4x7B-v3-Q2_K.gguf +3 -0
  7. Beyonder-4x7B-v3-Q3_K_L.gguf +3 -0
  8. Beyonder-4x7B-v3-Q3_K_M.gguf +3 -0
  9. Beyonder-4x7B-v3-Q3_K_S.gguf +3 -0
  10. Beyonder-4x7B-v3-Q4_0.gguf +3 -0
  11. Beyonder-4x7B-v3-Q4_K_M.gguf +3 -0
  12. Beyonder-4x7B-v3-Q4_K_S.gguf +3 -0
  13. Beyonder-4x7B-v3-Q5_0.gguf +3 -0
  14. Beyonder-4x7B-v3-Q5_K_M.gguf +3 -0
  15. Beyonder-4x7B-v3-Q5_K_S.gguf +3 -0
  16. Beyonder-4x7B-v3-Q6_K.gguf +3 -0
  17. Beyonder-4x7B-v3-Q8_0.gguf +3 -0
  18. README.md +45 -0
.gitattributes CHANGED
@@ -33,3 +33,19 @@ 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
+ Beyonder-4x7B-v3-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Beyonder-4x7B-v3-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Beyonder-4x7B-v3-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Beyonder-4x7B-v3-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Beyonder-4x7B-v3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Beyonder-4x7B-v3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Beyonder-4x7B-v3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Beyonder-4x7B-v3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Beyonder-4x7B-v3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Beyonder-4x7B-v3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Beyonder-4x7B-v3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Beyonder-4x7B-v3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Beyonder-4x7B-v3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Beyonder-4x7B-v3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Beyonder-4x7B-v3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Beyonder-4x7B-v3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Beyonder-4x7B-v3-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c55de31bff49305a8e62f2157336fb58f3c94114817ed09185a32e863a4506
3
+ size 10646177760
Beyonder-4x7B-v3-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abc106a4b69db2235962b6cadaa7d34f4cc931f130fbd0a0582be079a8270d5
3
+ size 10450094048
Beyonder-4x7B-v3-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac16bb4096934da6695613ee9f1fa4870da0cc6c48df070aac9feda94e429a75
3
+ size 13756884960
Beyonder-4x7B-v3-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b1cfe848c783b973dd70a6d81dc5091150a7ddf217cccad4efcb7c3db98795
3
+ size 13039757280
Beyonder-4x7B-v3-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f5a4cbef7ffd85d0ff28440abb3dfae5aa350790cd0387b2a7b26d84e98941
3
+ size 8841897952
Beyonder-4x7B-v3-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb5245c4f09b1298c5e6a009e256ea1764ab214f55edb4cd0dde502a564093a
3
+ size 12543051744
Beyonder-4x7B-v3-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40a5291dbcbbdcd43263c28e3ae598ffd17ac7345f068c0f4e941daf2065e3c
3
+ size 11579410400
Beyonder-4x7B-v3-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f197a16cc3de45096346c31dfb29cff68ad16a0810a93d0e7371891ac26f9217
3
+ size 10432268256
Beyonder-4x7B-v3-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1acccaf75329e8b40dac5063e88f06b4fa58f4001e5c25e85f818b9775eaafa
3
+ size 13622667232
Beyonder-4x7B-v3-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126e2f0b280388bcf563df6df18986f1212d868f7967765932e0960274db6a9e
3
+ size 14608852960
Beyonder-4x7B-v3-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83958c4cd28bcfc46d793281aa201a359757c6af17e485b8be396582245d727
3
+ size 13742204896
Beyonder-4x7B-v3-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a8f925059a958982e8c93463a67693ffa07efe9975adf3e81c61fcf3b97b93
3
+ size 16625395680
Beyonder-4x7B-v3-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d77af454e2951893077e451f70319ae726edd9062267b5269d17fc0cb928c0f
3
+ size 17133430752
Beyonder-4x7B-v3-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70af960625c18c3e89f790244a0256f32e2e328769f6a96f8257c9830bf624c
3
+ size 16625395680
Beyonder-4x7B-v3-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d36dfe9cdfa82a0b6aeb6dc5f214fb9c98b7425433c9b58cfe2d62932fa3831
3
+ size 19815794656
Beyonder-4x7B-v3-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249fc532416aeea7c738ce9b519f5f807c9c45a609183a9ab7a6f1eeb2b8b28b
3
+ size 25665325024
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ base_model:
10
+ - mlabonne/AlphaMonarch-7B
11
+ - beowolx/CodeNinja-1.0-OpenChat-7B
12
+ - SanjiWatsuki/Kunoichi-DPO-v2-7B
13
+ - mlabonne/NeuralDaredevil-7B
14
+ quantized_by: bartowski
15
+ pipeline_tag: text-generation
16
+ ---
17
+
18
+ ## Llamacpp Quantizations of Beyonder-4x7B-v3
19
+
20
+ 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.
21
+
22
+ Original model: https://huggingface.co/mlabonne/Beyonder-4x7B-v3
23
+
24
+ Download a file (not the whole branch) from below:
25
+
26
+ | Filename | Quant type | File Size | Description |
27
+ | -------- | ---------- | --------- | ----------- |
28
+ | [Beyonder-4x7B-v3-Q8_0.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q8_0.gguf) | Q8_0 | 25.66GB | Extremely high quality, generally unneeded but max available quant. |
29
+ | [Beyonder-4x7B-v3-Q6_K.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q6_K.gguf) | Q6_K | 19.81GB | Very high quality, near perfect, *recommended*. |
30
+ | [Beyonder-4x7B-v3-Q5_K_M.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q5_K_M.gguf) | Q5_K_M | 17.13GB | High quality, very usable. |
31
+ | [Beyonder-4x7B-v3-Q5_K_S.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q5_K_S.gguf) | Q5_K_S | 16.62GB | High quality, very usable. |
32
+ | [Beyonder-4x7B-v3-Q5_0.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q5_0.gguf) | Q5_0 | 16.62GB | High quality, older format, generally not recommended. |
33
+ | [Beyonder-4x7B-v3-Q4_K_M.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q4_K_M.gguf) | Q4_K_M | 14.60GB | Good quality, similar to 4.25 bpw. |
34
+ | [Beyonder-4x7B-v3-Q4_K_S.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q4_K_S.gguf) | Q4_K_S | 13.74GB | Slightly lower quality with small space savings. |
35
+ | [Beyonder-4x7B-v3-IQ4_NL.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-IQ4_NL.gguf) | IQ4_NL | 13.75GB | Good quality, similar to Q4_K_S, new method of quanting, |
36
+ | [Beyonder-4x7B-v3-IQ4_XS.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-IQ4_XS.gguf) | IQ4_XS | 13.03GB | Decent quality, new method with similar performance to Q4. |
37
+ | [Beyonder-4x7B-v3-Q4_0.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q4_0.gguf) | Q4_0 | 13.62GB | Decent quality, older format, generally not recommended. |
38
+ | [Beyonder-4x7B-v3-IQ3_M.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-IQ3_M.gguf) | IQ3_M | 10.64GB | Medium-low quality, new method with decent performance. |
39
+ | [Beyonder-4x7B-v3-IQ3_S.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-IQ3_S.gguf) | IQ3_S | 10.45GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
40
+ | [Beyonder-4x7B-v3-Q3_K_L.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q3_K_L.gguf) | Q3_K_L | 12.54GB | Lower quality but usable, good for low RAM availability. |
41
+ | [Beyonder-4x7B-v3-Q3_K_M.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q3_K_M.gguf) | Q3_K_M | 11.57GB | Even lower quality. |
42
+ | [Beyonder-4x7B-v3-Q3_K_S.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q3_K_S.gguf) | Q3_K_S | 10.43GB | Low quality, not recommended. |
43
+ | [Beyonder-4x7B-v3-Q2_K.gguf](https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF/blob/main/Beyonder-4x7B-v3-Q2_K.gguf) | Q2_K | 8.84GB | Extremely low quality, *not* recommended.
44
+
45
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski