Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- NuminaMath-7B-TIR-Q2_K.gguf +3 -0
- NuminaMath-7B-TIR-Q3_K_L.gguf +3 -0
- NuminaMath-7B-TIR-Q3_K_M.gguf +3 -0
- NuminaMath-7B-TIR-Q3_K_S.gguf +3 -0
- NuminaMath-7B-TIR-Q4_0.gguf +3 -0
- NuminaMath-7B-TIR-Q4_K_M.gguf +3 -0
- NuminaMath-7B-TIR-Q4_K_S.gguf +3 -0
- NuminaMath-7B-TIR-Q5_0.gguf +3 -0
- NuminaMath-7B-TIR-Q5_K_M.gguf +3 -0
- NuminaMath-7B-TIR-Q5_K_S.gguf +3 -0
- NuminaMath-7B-TIR-Q6_K.gguf +3 -0
- NuminaMath-7B-TIR-Q8_0.gguf +3 -0
- README.md +110 -0
.gitattributes
CHANGED
@@ -33,3 +33,15 @@ 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 |
+
NuminaMath-7B-TIR-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
NuminaMath-7B-TIR-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
NuminaMath-7B-TIR-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
NuminaMath-7B-TIR-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
NuminaMath-7B-TIR-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
NuminaMath-7B-TIR-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
NuminaMath-7B-TIR-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
NuminaMath-7B-TIR-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
NuminaMath-7B-TIR-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
NuminaMath-7B-TIR-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
NuminaMath-7B-TIR-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
NuminaMath-7B-TIR-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
NuminaMath-7B-TIR-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c063e1065862adba4a9cd9c0bb9805831d761d3ca3164fbb1d7ec1af8addfdb8
|
3 |
+
size 2718423200
|
NuminaMath-7B-TIR-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25d3000bc4d535e972d648233e5dee1c689eda3c6bed6d44e6d2279260b53740
|
3 |
+
size 3746273440
|
NuminaMath-7B-TIR-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a371169d707d2c14f32de04a6e0b9a185f6d1e6c4a8bee2e296490c1c76eacbd
|
3 |
+
size 3461191840
|
NuminaMath-7B-TIR-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be89a2dccb791758403044f548f67cd1cb61c74b4c98da4e5e46fa2cf9af38ad
|
3 |
+
size 3138017440
|
NuminaMath-7B-TIR-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d2b3d8b44f769df43dc9a386ccf127f2ab1dd972d645d4df2cd69bb607d0ef3
|
3 |
+
size 4000061600
|
NuminaMath-7B-TIR-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e67c6537b0893606a31b8885ef757a8fa1c1855c3600e882e655ba769d292d1d
|
3 |
+
size 4223359136
|
NuminaMath-7B-TIR-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16e9a40a486fa322f3056634b73533d0b7a80b5bf170c27b1e47e91a16590eb8
|
3 |
+
size 4025358496
|
NuminaMath-7B-TIR-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed832423a9ab451b2e9031cf966ff310c885c6ba9a97028c16996978961f12ac
|
3 |
+
size 4811397280
|
NuminaMath-7B-TIR-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cfd8bbb4bb71510f5d85d1ab66a0db8dcf47298eef4636f79e7e92e3356e3b8
|
3 |
+
size 4926429344
|
NuminaMath-7B-TIR-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fee349e4d1c29f1c399aabaf80f8f1c12543a65b69243e65ac61ede6a83f809
|
3 |
+
size 4811397280
|
NuminaMath-7B-TIR-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b992c4f410605bd2ea1da2b4d4007d6c908cabbf055402efb1ddb562848286e
|
3 |
+
size 5673441440
|
NuminaMath-7B-TIR-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd11958260b6873374ab923c027144473af4644534a2247336511bee0e07ad95
|
3 |
+
size 7346985120
|
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: AI-MO/NuminaMath-7B-TIR
|
3 |
+
tags:
|
4 |
+
- alignment-handbook
|
5 |
+
- generated_from_trainer
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
widget:
|
9 |
+
- example_title: Math problem
|
10 |
+
messages:
|
11 |
+
- role: user
|
12 |
+
content: For how many values of the constant $k$ will the polynomial $x^{2}+kx+36$
|
13 |
+
have two distinct integer roots?
|
14 |
+
output:
|
15 |
+
text: "### Solution: \n1- For the polynomial \\\\( x^2 + kx + 36 \\\\) to have\
|
16 |
+
\ two distinct integer roots, let's denote these roots by \\\\( r_1 \\\\) and\
|
17 |
+
\ \\\\( r_2 \\\\).\n\n\n2- According to Vieta's formulas, the sum of the roots\
|
18 |
+
\ \\\\( r_1 + r_2 \\\\) is equal to \\\\(-k\\\\), and the product of the roots\
|
19 |
+
\ \\\\( r_1 \\\\cdot r_2 \\\\) is equal to 36.\n\n\n3- To find the distinct\
|
20 |
+
\ integer pairs \\\\((r_1, r_2)\\\\) whose product is 36, we need to determine\
|
21 |
+
\ all pairs of integers \\\\((r_1, r_2)\\\\) such that \\\\( r_1 \\\\cdot r_2\
|
22 |
+
\ = 36 \\\\) and \\\\( r_1 \\\\neq r_2 \\\\).\n\n\n4- From the equation \\\\\
|
23 |
+
( r_1 + r_2 = -k \\\\), for each valid pair \\\\((r_1, r_2)\\\\), we can compute\
|
24 |
+
\ the corresponding value of \\\\( k \\\\).\n\n\n5- Finally, since we need the\
|
25 |
+
\ polynomial to have two distinct integer roots, we need to ensure that \\\\\
|
26 |
+
( r_1 \\\\) and \\\\( r_2 \\\\) are distinct.\nLet's start by finding all pairs\
|
27 |
+
\ \\\\((r_1, r_2)\\\\) such that \\\\( r_1 \\\\cdot r_2 = 36 \\\\). We'll then\
|
28 |
+
\ determine the values of \\\\( k \\\\) and ensure the roots are distinct.\n\
|
29 |
+
```python import itertools\n# Find all pairs (r1, r2) such that r1 * r2 = 36\
|
30 |
+
\ product_36 = 36 factor_pairs = []\nfor i in range(1, product_36 + 1):\n if\
|
31 |
+
\ product_36 % i == 0:\n pair = (i, product_36 // i)\n if pair[0] != pair[1]:\
|
32 |
+
\ # Ensure distinct pairs\n factor_pairs.append(pair)\n \n # Calculate\
|
33 |
+
\ k for each pair and ensure distinct integer roots\n valid_k_values = set()\n\
|
34 |
+
\ for r1, r2 in factor_pairs:\n if r1 != r2:\n k = -(r1 + r2)\n\
|
35 |
+
\ valid_k_values.add(k)\n \n print((len(valid_k_values), sorted(valid_k_values)))\n\
|
36 |
+
\ ```\n \n ```output\n (4, [-37, -20, -15,-13])\n ```\n The distinct integer\
|
37 |
+
\ values of \\\\( k \\\\) that make the\npolynomial \\\\( x^2 + kx + 36 \\\\\
|
38 |
+
) have two distinct integer roots are \\\\(-37, -20, -15, \\\\text{and} -13\\\
|
39 |
+
\\).\nTherefore, the number of such values of \\\\( k \\\\) is:\n[ \\\\boxed{4}\
|
40 |
+
\ \\\\]"
|
41 |
+
pipeline_tag: text-generation
|
42 |
+
license: apache-2.0
|
43 |
+
model-index:
|
44 |
+
- name: NuminaMath-7B-TIR
|
45 |
+
results: []
|
46 |
+
---
|
47 |
+
|
48 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
49 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
50 |
+
</div>
|
51 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
52 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
53 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
54 |
+
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
|
55 |
+
</p>
|
56 |
+
</div>
|
57 |
+
</div>
|
58 |
+
|
59 |
+
## AI-MO/NuminaMath-7B-TIR - GGUF
|
60 |
+
|
61 |
+
This repo contains GGUF format model files for [AI-MO/NuminaMath-7B-TIR](https://huggingface.co/AI-MO/NuminaMath-7B-TIR).
|
62 |
+
|
63 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
64 |
+
|
65 |
+
## Prompt template
|
66 |
+
|
67 |
+
```
|
68 |
+
### Problem: {prompt}
|
69 |
+
### Solution:
|
70 |
+
```
|
71 |
+
|
72 |
+
## Model file specification
|
73 |
+
|
74 |
+
| Filename | Quant type | File Size | Description |
|
75 |
+
| -------- | ---------- | --------- | ----------- |
|
76 |
+
| [NuminaMath-7B-TIR-Q2_K.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
|
77 |
+
| [NuminaMath-7B-TIR-Q3_K_S.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q3_K_S.gguf) | Q3_K_S | 2.923 GB | very small, high quality loss |
|
78 |
+
| [NuminaMath-7B-TIR-Q3_K_M.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q3_K_M.gguf) | Q3_K_M | 3.223 GB | very small, high quality loss |
|
79 |
+
| [NuminaMath-7B-TIR-Q3_K_L.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q3_K_L.gguf) | Q3_K_L | 3.489 GB | small, substantial quality loss |
|
80 |
+
| [NuminaMath-7B-TIR-Q4_0.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q4_0.gguf) | Q4_0 | 3.725 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
81 |
+
| [NuminaMath-7B-TIR-Q4_K_S.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q4_K_S.gguf) | Q4_K_S | 3.749 GB | small, greater quality loss |
|
82 |
+
| [NuminaMath-7B-TIR-Q4_K_M.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q4_K_M.gguf) | Q4_K_M | 3.933 GB | medium, balanced quality - recommended |
|
83 |
+
| [NuminaMath-7B-TIR-Q5_0.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q5_0.gguf) | Q5_0 | 4.481 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
84 |
+
| [NuminaMath-7B-TIR-Q5_K_S.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q5_K_S.gguf) | Q5_K_S | 4.481 GB | large, low quality loss - recommended |
|
85 |
+
| [NuminaMath-7B-TIR-Q5_K_M.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q5_K_M.gguf) | Q5_K_M | 4.588 GB | large, very low quality loss - recommended |
|
86 |
+
| [NuminaMath-7B-TIR-Q6_K.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q6_K.gguf) | Q6_K | 5.284 GB | very large, extremely low quality loss |
|
87 |
+
| [NuminaMath-7B-TIR-Q8_0.gguf](https://huggingface.co/tensorblock/NuminaMath-7B-TIR-GGUF/tree/main/NuminaMath-7B-TIR-Q8_0.gguf) | Q8_0 | 6.842 GB | very large, extremely low quality loss - not recommended |
|
88 |
+
|
89 |
+
|
90 |
+
## Downloading instruction
|
91 |
+
|
92 |
+
### Command line
|
93 |
+
|
94 |
+
Firstly, install Huggingface Client
|
95 |
+
|
96 |
+
```shell
|
97 |
+
pip install -U "huggingface_hub[cli]"
|
98 |
+
```
|
99 |
+
|
100 |
+
Then, downoad the individual model file the a local directory
|
101 |
+
|
102 |
+
```shell
|
103 |
+
huggingface-cli download tensorblock/NuminaMath-7B-TIR-GGUF --include "NuminaMath-7B-TIR-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
104 |
+
```
|
105 |
+
|
106 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
107 |
+
|
108 |
+
```shell
|
109 |
+
huggingface-cli download tensorblock/NuminaMath-7B-TIR-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
110 |
+
```
|