bartowski
commited on
Commit
·
9d9d2b7
verified
·
0
Parent(s):
Duplicate from bartowski/internlm2-math-plus-mixtral8x22b-GGUF
Browse files- .gitattributes +67 -0
- README.md +96 -0
- internlm2-math-plus-mixtral8x22b-IQ1_M.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ2_M.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ2_S.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ2_XXS.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ3_M.gguf/internlm2-math-plus-mixtral8x22b-IQ3_M-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ3_M.gguf/internlm2-math-plus-mixtral8x22b-IQ3_M-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ3_XS-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ3_XS-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ4_XS-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ4_XS-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q2_K.gguf/internlm2-math-plus-mixtral8x22b-Q2_K-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q2_K.gguf/internlm2-math-plus-mixtral8x22b-Q2_K-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q3_K_M-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q3_K_M-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_M-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_M-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_S-00001-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_S-00002-of-00002.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00001-of-00003.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00002-of-00003.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00003-of-00003.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00001-of-00003.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00002-of-00003.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00003-of-00003.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00001-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00002-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00003-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00004-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00005-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00006-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00007-of-00007.gguf +3 -0
- internlm2-math-plus-mixtral8x22b.imatrix +3 -0
.gitattributes
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
internlm2-math-plus-mixtral8x22b-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
internlm2-math-plus-mixtral8x22b-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
internlm2-math-plus-mixtral8x22b-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
internlm2-math-plus-mixtral8x22b-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
internlm2-math-plus-mixtral8x22b-IQ3_M.gguf/internlm2-math-plus-mixtral8x22b-IQ3_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
internlm2-math-plus-mixtral8x22b-IQ3_M.gguf/internlm2-math-plus-mixtral8x22b-IQ3_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ3_XS-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ3_XS-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ4_XS-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ4_XS-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
internlm2-math-plus-mixtral8x22b-Q2_K.gguf/internlm2-math-plus-mixtral8x22b-Q2_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
internlm2-math-plus-mixtral8x22b-Q2_K.gguf/internlm2-math-plus-mixtral8x22b-Q2_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q3_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q3_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
50 |
+
internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
51 |
+
internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
52 |
+
internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_S-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
53 |
+
internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_S-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
54 |
+
internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
55 |
+
internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
56 |
+
internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
57 |
+
internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
58 |
+
internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
59 |
+
internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
60 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00001-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
61 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00002-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
62 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00003-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
63 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00004-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
64 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
65 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00006-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
66 |
+
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00007-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
|
67 |
+
internlm2-math-plus-mixtral8x22b.imatrix filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: text-generation
|
3 |
+
license: other
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
- zh
|
7 |
+
tags:
|
8 |
+
- math
|
9 |
+
quantized_by: bartowski
|
10 |
+
---
|
11 |
+
|
12 |
+
## Llamacpp imatrix Quantizations of internlm2-math-plus-mixtral8x22b
|
13 |
+
|
14 |
+
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3001">b3001</a> for quantization.
|
15 |
+
|
16 |
+
Original model: https://huggingface.co/internlm/internlm2-math-plus-mixtral8x22b
|
17 |
+
|
18 |
+
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
19 |
+
|
20 |
+
## Prompt format
|
21 |
+
|
22 |
+
No chat template specified so default is used. This may be incorrect, check original model card for details.
|
23 |
+
|
24 |
+
```
|
25 |
+
<s> [INST] <<SYS>>
|
26 |
+
{system_prompt}
|
27 |
+
<</SYS>>
|
28 |
+
|
29 |
+
{prompt} [/INST] </s>
|
30 |
+
```
|
31 |
+
|
32 |
+
## Download a file (not the whole branch) from below:
|
33 |
+
|
34 |
+
| Filename | Quant type | File Size | Description |
|
35 |
+
| -------- | ---------- | --------- | ----------- |
|
36 |
+
| [internlm2-math-plus-mixtral8x22b-Q6_K.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-Q6_K.gguf) | Q6_K | 115.53GB | Very high quality, near perfect, *recommended*. |
|
37 |
+
| [internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf) | Q5_K_M | 99.97GB | High quality, *recommended*. |
|
38 |
+
| [internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf) | Q4_K_M | 85.59GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
|
39 |
+
| [internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf) | Q4_K_S | 80.48GB | Slightly lower quality with more space savings, *recommended*. |
|
40 |
+
| [internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf) | IQ4_XS | 75.47GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
41 |
+
| [internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf) | Q3_K_M | 67.79GB | Even lower quality. |
|
42 |
+
| [internlm2-math-plus-mixtral8x22b-IQ3_M.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-IQ3_M.gguf) | IQ3_M | 64.49GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
43 |
+
| [internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf) | IQ3_XS | 58.23GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
44 |
+
| [internlm2-math-plus-mixtral8x22b-Q2_K.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/tree/main/internlm2-math-plus-mixtral8x22b-Q2_K.gguf) | Q2_K | 52.10GB | Very low quality but surprisingly usable. |
|
45 |
+
| [internlm2-math-plus-mixtral8x22b-IQ2_M.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/blob/main/internlm2-math-plus-mixtral8x22b-IQ2_M.gguf) | IQ2_M | 46.71GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
|
46 |
+
| [internlm2-math-plus-mixtral8x22b-IQ2_S.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/blob/main/internlm2-math-plus-mixtral8x22b-IQ2_S.gguf) | IQ2_S | 42.59GB | Very low quality, uses SOTA techniques to be usable. |
|
47 |
+
| [internlm2-math-plus-mixtral8x22b-IQ2_XXS.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/blob/main/internlm2-math-plus-mixtral8x22b-IQ2_XXS.gguf) | IQ2_XXS | 37.88GB | Lower quality, uses SOTA techniques to be usable. |
|
48 |
+
| [internlm2-math-plus-mixtral8x22b-IQ1_M.gguf](https://huggingface.co/bartowski/internlm2-math-plus-mixtral8x22b-GGUF/blob/main/internlm2-math-plus-mixtral8x22b-IQ1_M.gguf) | IQ1_M | 32.73GB | Extremely low quality, *not* recommended. |
|
49 |
+
|
50 |
+
## Downloading using huggingface-cli
|
51 |
+
|
52 |
+
First, make sure you have hugginface-cli installed:
|
53 |
+
|
54 |
+
```
|
55 |
+
pip install -U "huggingface_hub[cli]"
|
56 |
+
```
|
57 |
+
|
58 |
+
Then, you can target the specific file you want:
|
59 |
+
|
60 |
+
```
|
61 |
+
huggingface-cli download bartowski/internlm2-math-plus-mixtral8x22b-GGUF --include "internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf" --local-dir ./
|
62 |
+
```
|
63 |
+
|
64 |
+
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
|
65 |
+
|
66 |
+
```
|
67 |
+
huggingface-cli download bartowski/internlm2-math-plus-mixtral8x22b-GGUF --include "internlm2-math-plus-mixtral8x22b-Q8_0.gguf/*" --local-dir internlm2-math-plus-mixtral8x22b-Q8_0
|
68 |
+
```
|
69 |
+
|
70 |
+
You can either specify a new local-dir (internlm2-math-plus-mixtral8x22b-Q8_0) or download them all in place (./)
|
71 |
+
|
72 |
+
## Which file should I choose?
|
73 |
+
|
74 |
+
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
|
75 |
+
|
76 |
+
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
|
77 |
+
|
78 |
+
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
|
79 |
+
|
80 |
+
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
|
81 |
+
|
82 |
+
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
|
83 |
+
|
84 |
+
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
|
85 |
+
|
86 |
+
If you want to get more into the weeds, you can check out this extremely useful feature chart:
|
87 |
+
|
88 |
+
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
|
89 |
+
|
90 |
+
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
|
91 |
+
|
92 |
+
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
93 |
+
|
94 |
+
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
|
95 |
+
|
96 |
+
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
internlm2-math-plus-mixtral8x22b-IQ1_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d166be7a46189b40ac05b4fdca7f5a78dd8c2bc93ebafaec42023893f46703e
|
3 |
+
size 32738304160
|
internlm2-math-plus-mixtral8x22b-IQ2_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8321f098b7690b7724433acea3d17188a07b3ce85c31eb5df87744dd95e9aa91
|
3 |
+
size 46713547936
|
internlm2-math-plus-mixtral8x22b-IQ2_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fb64dcc30ec63d2c0f3a2fdd483587f745df49bd5bab3197a05c803e23d3de7
|
3 |
+
size 42595789984
|
internlm2-math-plus-mixtral8x22b-IQ2_XXS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6771ac5216b14b49f7ba04ebf364e4db4fcab9b5d86b9f9989f884ee4cd6728
|
3 |
+
size 37885501600
|
internlm2-math-plus-mixtral8x22b-IQ3_M.gguf/internlm2-math-plus-mixtral8x22b-IQ3_M-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:523f21f94b91333c69d042fd6e30e207bc9947754b161d8055b1d18733834b3d
|
3 |
+
size 42778869312
|
internlm2-math-plus-mixtral8x22b-IQ3_M.gguf/internlm2-math-plus-mixtral8x22b-IQ3_M-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9014c2335eca4fd3f6b499be1524c96080840f009cceb5e116c5d18548ace04d
|
3 |
+
size 21720050464
|
internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ3_XS-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb615cad074a2fa9a4bfb64416f0a0505d271d93088342a000b8fd772a1d5242
|
3 |
+
size 42657171552
|
internlm2-math-plus-mixtral8x22b-IQ3_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ3_XS-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb3c82b2279ab4067417655b955328012ce16d4d866c9ef26aede2baa4a1735
|
3 |
+
size 15577030912
|
internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ4_XS-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c2b82e0cac6b1398051f93d17cf1ee4ee70d7a6ec08ad1850b2744ff39f5ef1
|
3 |
+
size 42656037760
|
internlm2-math-plus-mixtral8x22b-IQ4_XS.gguf/internlm2-math-plus-mixtral8x22b-IQ4_XS-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5130ac46eae6eea292162d00faa29f114b8b2544adc0977dab006edb040b637b
|
3 |
+
size 32823392736
|
internlm2-math-plus-mixtral8x22b-Q2_K.gguf/internlm2-math-plus-mixtral8x22b-Q2_K-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac3aae73436425eb077450ee611bfe65dba2f875fb8f950b619b2c6ad7e2770e
|
3 |
+
size 42734733472
|
internlm2-math-plus-mixtral8x22b-Q2_K.gguf/internlm2-math-plus-mixtral8x22b-Q2_K-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1229a6ab679e92dceed214368c5dc306fd9790d2d03fed1b289d77ebb1fb1b91
|
3 |
+
size 9374389440
|
internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q3_K_M-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:074fefb42b5f968a0cd114b2a70f482e5f818c780a2697794a31e082d8f2a2a7
|
3 |
+
size 42818287936
|
internlm2-math-plus-mixtral8x22b-Q3_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q3_K_M-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c214cfa5f566f6e7dc3faacc0d8972136095fc7e66c4b452a8da68f65aabc45
|
3 |
+
size 24977354784
|
internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_M-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422263ef035a2a6c10d46a04f820127a88c74f4a7eca7f700431e1a7f060e09b
|
3 |
+
size 42832110432
|
internlm2-math-plus-mixtral8x22b-Q4_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_M-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73269b3fa2046936e7defc3c2ca3e181cada8c60a1c946cd7f18b80fae58704c
|
3 |
+
size 42760700416
|
internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_S-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e60814c8b16ad243b8e8b5a3a6a3292fad0b7049a06b35676116fa9b8260c94f
|
3 |
+
size 42502841888
|
internlm2-math-plus-mixtral8x22b-Q4_K_S.gguf/internlm2-math-plus-mixtral8x22b-Q4_K_S-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c0ff8d4ab8ec25e64fd31b677dba22deda7152bb35795c46352e94c998966c6
|
3 |
+
size 37981306656
|
internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00001-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4469b438298ea0055b58cb05b4da3b33b9dab6e039369c58e21329961152c679
|
3 |
+
size 42887403680
|
internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00002-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903ff40a6e01c2ac5690a53b8905aedd62234a9144f1c001e7b05309f659ae61
|
3 |
+
size 42877271488
|
internlm2-math-plus-mixtral8x22b-Q5_K_M.gguf/internlm2-math-plus-mixtral8x22b-Q5_K_M-00003-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a976e0904fa2f68b4c553cefcaab41a52a0f2a8fbce3b6f3df855a0200e2e7ab
|
3 |
+
size 14209863552
|
internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00001-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75aa50a451afdd2a46731a84d31b49ae0daa5966ae7c3cbd9a83b9cb207b5c3e
|
3 |
+
size 42706144224
|
internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00002-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:507209f35de32bbe43c1889ee72b6895d6e4febdc5c755f6a9ab4a0ea64497b8
|
3 |
+
size 42543871200
|
internlm2-math-plus-mixtral8x22b-Q6_K.gguf/internlm2-math-plus-mixtral8x22b-Q6_K-00003-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a156f94db37ff250ea62e62284529d64a773091a1971979fe76e8d9b239070
|
3 |
+
size 30285865216
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00001-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e00a87b68bfec66235d25592eb9b8bda1eebaf20ed62f190c3674b4b60d8f9a
|
3 |
+
size 42247655520
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00002-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cce2c73f11b570b767cbb03b97c124cf8b35a0e2c0e1a74b13b06c45cd93764b
|
3 |
+
size 41676575936
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00003-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3bca5a1919b32b7deadae8d4c3fa204a127817e0730dfac93cc3964f200bbd2
|
3 |
+
size 41752122752
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00004-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfc87b78c5d1abcc1c1f2cdffbb9eb463f6b688a0f039627fae026e04cce1fc2
|
3 |
+
size 41777436128
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00005-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6cb0dbf68ce7031d3acafa66e60a7b8f39e8768cee3eb9eee9b43a9b4c7f5ab
|
3 |
+
size 41676575968
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00006-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b49cad502d81d8ac4055af9175972e7ab8d52d5fff4c604ee921993ae7d8910
|
3 |
+
size 41777288704
|
internlm2-math-plus-mixtral8x22b-f16.gguf/internlm2-math-plus-mixtral8x22b-f16-00007-of-00007.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44465b709e560d699d2d2844930277fd0d1bb1ea404fa09c1163cf69bfc3fc25
|
3 |
+
size 30342836032
|
internlm2-math-plus-mixtral8x22b.imatrix
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdd0a591713ca5af1d6c654b3950e15a3ab0c02168b31e9ecb10ce6a6fc33883
|
3 |
+
size 58277489
|