Hugging Face's logo

bartowski
/
Code-Mistral-7B-GGUF

Text Generation
GGUF
English
code
mathematics
Inference Endpoints
conversational
Model card Files Community
bartowski commited on
Commit
4665925
•
1 Parent(s): ce80b31

Llamacpp quants

Browse files
Files changed (18) hide show
  1. .gitattributes +16 -0
  2. Code-Mistral-7B-IQ3_M.gguf +3 -0
  3. Code-Mistral-7B-IQ3_S.gguf +3 -0
  4. Code-Mistral-7B-IQ4_NL.gguf +3 -0
  5. Code-Mistral-7B-IQ4_XS.gguf +3 -0
  6. Code-Mistral-7B-Q2_K.gguf +3 -0
  7. Code-Mistral-7B-Q3_K_L.gguf +3 -0
  8. Code-Mistral-7B-Q3_K_M.gguf +3 -0
  9. Code-Mistral-7B-Q3_K_S.gguf +3 -0
  10. Code-Mistral-7B-Q4_0.gguf +3 -0
  11. Code-Mistral-7B-Q4_K_M.gguf +3 -0
  12. Code-Mistral-7B-Q4_K_S.gguf +3 -0
  13. Code-Mistral-7B-Q5_0.gguf +3 -0
  14. Code-Mistral-7B-Q5_K_M.gguf +3 -0
  15. Code-Mistral-7B-Q5_K_S.gguf +3 -0
  16. Code-Mistral-7B-Q6_K.gguf +3 -0
  17. Code-Mistral-7B-Q8_0.gguf +3 -0
  18. README.md +44 -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
+ Code-Mistral-7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Code-Mistral-7B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Code-Mistral-7B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Code-Mistral-7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Code-Mistral-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Code-Mistral-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Code-Mistral-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Code-Mistral-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Code-Mistral-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Code-Mistral-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Code-Mistral-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Code-Mistral-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Code-Mistral-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Code-Mistral-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Code-Mistral-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Code-Mistral-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Code-Mistral-7B-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba58b01476c07b2dd7bf2e94bf16d83cb1a0e2fb32fbd29718c8257a3f92a755
3
+ size 3284892096
Code-Mistral-7B-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c67347404fa9deae18e90f0ea863fd33d7e5c2c6fddd9c0b8f9c09da8700e8
3
+ size 3182393792
Code-Mistral-7B-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df31ef6e53222527576c2525aa4c045c78c9c98986fbad00072ed0bb71e7fea5
3
+ size 4155054528
Code-Mistral-7B-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe115f928e828f5f34b5daca8a3311505dfe2fbf02801e96faa3b0d1bdc2da4
3
+ size 3944389056
Code-Mistral-7B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69948d5ede8d3a871827dc83c5b85b4766924b44c04f593691f280fd434c5cda
3
+ size 2719242688
Code-Mistral-7B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc0391a5021ae6017281119120d1f626f4c52e7d5891ee7db78930abfe5fad1
3
+ size 3822025152
Code-Mistral-7B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0cfc546a7f7328151d976ce1660d6389a843a35b4874823ed76a1e0b214e0d5
3
+ size 3518986688
Code-Mistral-7B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164faf26fd312b5dea58862c858732ae2f70357a2b4c5c9e9f4de05ac940c175
3
+ size 3164568000
Code-Mistral-7B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752f3e626b80d7189d323887ba0d5e2ef9f1a57a94bf9234dc1f7abbc2b78a62
3
+ size 4108917184
Code-Mistral-7B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d245224e7dec37457eeaf70fecb24121ae65f85aa3dfcbed36ed235115af61
3
+ size 4368439744
Code-Mistral-7B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53073608463455969140e7050cb2d9ad8e4ab2afd89c3147dbe0e0e116c89759
3
+ size 4140374464
Code-Mistral-7B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337796a42344744494b3ecf2b2079cbcb324393678d9129ccd30c7f2a05b2f6e
3
+ size 4997716416
Code-Mistral-7B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a8b51c264d828276fb40b45276a2bf2f2635b82f8d2b586b4f5c8e0c4a0e05
3
+ size 5131409856
Code-Mistral-7B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c23f994cc79e2d7b894b1b9704e6efb5211aaf0f7e5dfc54d3a2764d05030f
3
+ size 4997716416
Code-Mistral-7B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47be15dde4a65e09e7aa7dcac043927d88da7087f3361d272c9f8587c6d9be67
3
+ size 5942065600
Code-Mistral-7B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5a03914655415c25397167aeadaf273f1accd8f2af6469a004ebb88d235b49
3
+ size 7695858112
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - ajibawa-2023/Code-290k-ShareGPT
5
+ - m-a-p/Code-Feedback
6
+ - microsoft/orca-math-word-problems-200k
7
+ - teknium/openhermes
8
+ language:
9
+ - en
10
+ tags:
11
+ - code
12
+ - mathematics
13
+ quantized_by: bartowski
14
+ pipeline_tag: text-generation
15
+ ---
16
+
17
+ ## Llamacpp Quantizations of Code-Mistral-7B
18
+
19
+ 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.
20
+
21
+ Original model: https://huggingface.co/ajibawa-2023/Code-Mistral-7B
22
+
23
+ Download a file (not the whole branch) from below:
24
+
25
+ | Filename | Quant type | File Size | Description |
26
+ | -------- | ---------- | --------- | ----------- |
27
+ | [Code-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
28
+ | [Code-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
29
+ | [Code-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
30
+ | [Code-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
31
+ | [Code-Mistral-7B-Q5_0.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
32
+ | [Code-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
33
+ | [Code-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
34
+ | [Code-Mistral-7B-IQ4_NL.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-IQ4_NL.gguf) | IQ4_NL | 4.15GB | Good quality, similar to Q4_K_S, new method of quanting, |
35
+ | [Code-Mistral-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-IQ4_XS.gguf) | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. |
36
+ | [Code-Mistral-7B-Q4_0.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
37
+ | [Code-Mistral-7B-IQ3_M.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. |
38
+ | [Code-Mistral-7B-IQ3_S.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
39
+ | [Code-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
40
+ | [Code-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
41
+ | [Code-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
42
+ | [Code-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/Code-Mistral-7B-GGUF/blob/main/Code-Mistral-7B-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
43
+
44
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski