Hugging Face's logo

nicoboss
/
KwaiCoder-DS-V2-Lite-Base-non-MLA-i1-GGUF

Transformers
GGUF
multilingual
code-generation
imatrix
conversational
Model card Files
xet
Community
nicoboss mradermacher commited on
Commit
ae95201
·
verified ·
0 Parent(s):

Duplicate from mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF

Browse files

Co-authored-by: team mradermacher <[email protected]>

Files changed (27) hide show
  1. .gitattributes +60 -0
  2. KwaiCoder-DS-V2-Lite-Base.i1-IQ1_M.gguf +3 -0
  3. KwaiCoder-DS-V2-Lite-Base.i1-IQ1_S.gguf +3 -0
  4. KwaiCoder-DS-V2-Lite-Base.i1-IQ2_M.gguf +3 -0
  5. KwaiCoder-DS-V2-Lite-Base.i1-IQ2_S.gguf +3 -0
  6. KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XS.gguf +3 -0
  7. KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XXS.gguf +3 -0
  8. KwaiCoder-DS-V2-Lite-Base.i1-IQ3_M.gguf +3 -0
  9. KwaiCoder-DS-V2-Lite-Base.i1-IQ3_S.gguf +3 -0
  10. KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XS.gguf +3 -0
  11. KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XXS.gguf +3 -0
  12. KwaiCoder-DS-V2-Lite-Base.i1-IQ4_NL.gguf +3 -0
  13. KwaiCoder-DS-V2-Lite-Base.i1-IQ4_XS.gguf +3 -0
  14. KwaiCoder-DS-V2-Lite-Base.i1-Q2_K.gguf +3 -0
  15. KwaiCoder-DS-V2-Lite-Base.i1-Q2_K_S.gguf +3 -0
  16. KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_L.gguf +3 -0
  17. KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_M.gguf +3 -0
  18. KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_S.gguf +3 -0
  19. KwaiCoder-DS-V2-Lite-Base.i1-Q4_0.gguf +3 -0
  20. KwaiCoder-DS-V2-Lite-Base.i1-Q4_1.gguf +3 -0
  21. KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_M.gguf +3 -0
  22. KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_S.gguf +3 -0
  23. KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_M.gguf +3 -0
  24. KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_S.gguf +3 -0
  25. KwaiCoder-DS-V2-Lite-Base.i1-Q6_K.gguf +3 -0
  26. README.md +79 -0
  27. imatrix.dat +3 -0
.gitattributes ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ imatrix.dat filter=lfs diff=lfs merge=lfs -text
37
+ KwaiCoder-DS-V2-Lite-Base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
41
+ KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
43
+ KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
44
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ KwaiCoder-DS-V2-Lite-Base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
46
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
47
+ KwaiCoder-DS-V2-Lite-Base.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
48
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
51
+ KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
52
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
53
+ KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
54
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
55
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
56
+ KwaiCoder-DS-V2-Lite-Base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
57
+ KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
58
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
59
+ KwaiCoder-DS-V2-Lite-Base.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
60
+ KwaiCoder-DS-V2-Lite-Base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
KwaiCoder-DS-V2-Lite-Base.i1-IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872cdf8f5fc965862d55170516bb81c40e11a225ba6f1bc840b8539285cba567
3
+ size 5236565504
KwaiCoder-DS-V2-Lite-Base.i1-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81a385a51fd73dd358313dc4e10e319b44cdf48a219885cda885a6a5cac0fdf
3
+ size 4994132480
KwaiCoder-DS-V2-Lite-Base.i1-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04f2fc4c2a6126cab5c685526c325a280fe6fa6d90bc1ae31b5381cf022dada
3
+ size 6328457728
KwaiCoder-DS-V2-Lite-Base.i1-IQ2_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c82034a663c3409431605d2556c4ce85536d3a6085acf1c6808309e71ca89de
3
+ size 6005213696
KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3703267daa798847c1ba4663c784bf37f22cc1a744a32256e292c045ca779cc
3
+ size 5967403520
KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f723a9402bec470a2a62c130496de38121f5de7c20a1a9628f7b893c8ee117f
3
+ size 5640620544
KwaiCoder-DS-V2-Lite-Base.i1-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c23751378cf60916868638f8844c17df317ccbe920b74567c7bc9c9a22fdcf
3
+ size 7553176064
KwaiCoder-DS-V2-Lite-Base.i1-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1210b1e6ed0f2bef864b171851dbf71fbbe8d26fde3b77784f9de067b4294db5
3
+ size 7487664640
KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5f75e3d44b4164201f58cc156da382fd3a084ee0d0beb0c920c77bee71ddec
3
+ size 7122858496
KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda186c0a2b37ab1846949c9f70ecf365f170a651bf8bdc73c686383aff333b3
3
+ size 6964058624
KwaiCoder-DS-V2-Lite-Base.i1-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3127dc4fd144b6a73cacc53bd346f9cd938b0f3dd324f84670a30efae62ddd
3
+ size 8905111040
KwaiCoder-DS-V2-Lite-Base.i1-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363e61772e27971d26299fe1e2865d947c977cf41b19b61b1f572bcbf51b71c7
3
+ size 8571594240
KwaiCoder-DS-V2-Lite-Base.i1-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3accf385983cea807ce15a901d3ea6d97e60995d8b186f061fdc6baa7d31ad5
3
+ size 6430465536
KwaiCoder-DS-V2-Lite-Base.i1-Q2_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e50fc0b13a233976e53c86cfc8230b341c991ea5d14ce0519d05a8fc2451ce3
3
+ size 6455377408
KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275e5da7dd938b471613386d7ab62670c210e6875da224ecc418a29272c5582a
3
+ size 8459399680
KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2c5b13bb3e574c28df3932942f353d958a76d0fc0a8ad8a03496cf55c0795f
3
+ size 8126607872
KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3468d486a798da16239f3236112ea565d8c386955422a96464c0559559696d1d
3
+ size 7487664640
KwaiCoder-DS-V2-Lite-Base.i1-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923aec009377b08c0be8a1ed967d720f4bbb25cd5c8d4936be1ef6ccee058436
3
+ size 8930301440
KwaiCoder-DS-V2-Lite-Base.i1-Q4_1.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7ba11dc183ab4261096ecf798359963de56b19d1ab7caa90d044dd310e72a5
3
+ size 9873438208
KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821cc8e9808d634041b3d03acb31945403f0a3c22e23e20377e5bed6978ba053
3
+ size 10364417536
KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd10e08b742fbe4c398502bfbac165c20c531e88ebb5bdc009551dd6923b6e1
3
+ size 9533609472
KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a6c1aac25eb40dc8f9da4e0d3457a28dfaee3e674a55b8dcb90de645354ec6
3
+ size 11851314688
KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42d2ce0b374d54a53a8a98103a0bd42684b7749a984f617a7243565b89573ba
3
+ size 11143058944
KwaiCoder-DS-V2-Lite-Base.i1-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2973f5b4994ee140ad2c2744f46f898b50e840919d8941e85a526b3761e3dc
3
+ size 14066973184
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Kwaipilot/KwaiCoder-DS-V2-Lite-Base
3
+ language:
4
+ - multilingual
5
+ library_name: transformers
6
+ license: mit
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - code-generation
10
+ - transformers
11
+ ---
12
+ ## About
13
+
14
+ <!-- ### quantize_version: 2 -->
15
+ <!-- ### output_tensor_quantised: 1 -->
16
+ <!-- ### convert_type: hf -->
17
+ <!-- ### vocab_type: -->
18
+ <!-- ### tags: nicoboss -->
19
+ weighted/imatrix quants of https://huggingface.co/Kwaipilot/KwaiCoder-DS-V2-Lite-Base
20
+
21
+ <!-- provided-files -->
22
+ static quants are available at https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-GGUF
23
+ ## Usage
24
+
25
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
26
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
27
+ more details, including on how to concatenate multi-part files.
28
+
29
+ ## Provided Quants
30
+
31
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
32
+
33
+ | Link | Type | Size/GB | Notes |
34
+ |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 5.1 | for the desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 5.3 | mostly desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.1 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 6.1 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 6.4 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q2_K.gguf) | i1-Q2_K | 6.5 | IQ3_XXS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.6 | very low quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.1 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ3_S.gguf) | i1-IQ3_S | 7.6 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 7.6 | IQ3_XS probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 7.7 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 8.2 | IQ3_S probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.6 | IQ3_M probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.7 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 9.0 | prefer IQ4_XS |
52
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q4_0.gguf) | i1-Q4_0 | 9.0 | fast, low quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 9.6 | optimal size/speed/quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q4_1.gguf) | i1-Q4_1 | 10.0 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 10.5 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 11.2 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 12.0 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/KwaiCoder-DS-V2-Lite-Base-i1-GGUF/resolve/main/KwaiCoder-DS-V2-Lite-Base.i1-Q6_K.gguf) | i1-Q6_K | 14.2 | practically like static Q6_K |
59
+
60
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
61
+ types (lower is better):
62
+
63
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
64
+
65
+ And here are Artefact2's thoughts on the matter:
66
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
67
+
68
+ ## FAQ / Model Request
69
+
70
+ See https://huggingface.co/mradermacher/model_requests for some answers to
71
+ questions you might have and/or if you want some other model quantized.
72
+
73
+ ## Thanks
74
+
75
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
76
+ me use its servers and providing upgrades to my workstation to enable
77
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
78
+
79
+ <!-- end -->
imatrix.dat ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408d119b024396b3f6b1b5b25d31931a4fab43d9ba8dc39a8daeb558589c7904
3
+ size 38356408