Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- OpenMath2-Llama3.1-8B-Q2_K.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q3_K_L.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q3_K_M.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q3_K_S.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q4_0.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q4_K_M.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q4_K_S.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q5_0.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q5_K_M.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q5_K_S.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q6_K.gguf +3 -0
- OpenMath2-Llama3.1-8B-Q8_0.gguf +3 -0
- README.md +87 -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 |
+
OpenMath2-Llama3.1-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
OpenMath2-Llama3.1-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
OpenMath2-Llama3.1-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
OpenMath2-Llama3.1-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
OpenMath2-Llama3.1-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
OpenMath2-Llama3.1-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
OpenMath2-Llama3.1-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
OpenMath2-Llama3.1-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
OpenMath2-Llama3.1-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
OpenMath2-Llama3.1-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
OpenMath2-Llama3.1-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
OpenMath2-Llama3.1-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
OpenMath2-Llama3.1-8B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ce6e58c2d0b0e9dc641c52e78173352ce60480d7d3e81b0036db353e48b6e68
|
3 |
+
size 3179136416
|
OpenMath2-Llama3.1-8B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f12e7505b2e2115ef2d959bfe53edeb77f8d5be0fccb40c11373a35ab526519
|
3 |
+
size 4321961376
|
OpenMath2-Llama3.1-8B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a203b6d6a67de7e1f764dee964a4caec11a482c738818d32a0310e1c9ff36868
|
3 |
+
size 4018922912
|
OpenMath2-Llama3.1-8B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aee83b72a36f00d4bd8e0762d1bba1c2d9ebe7c0d6c84ad12fc80824de05abc0
|
3 |
+
size 3664504224
|
OpenMath2-Llama3.1-8B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9a2124bbc16aae54703c204b47fc1d3cb2e5972dcc0a29ed12e7a3a0d414f06
|
3 |
+
size 4661216672
|
OpenMath2-Llama3.1-8B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0431cc0eae0add3f33c347793442b8117a21b348ee75cc96a12b0ad2d74db23d
|
3 |
+
size 4920739232
|
OpenMath2-Llama3.1-8B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3cdc2121c5fa06ffe549d6cc2461caee576f967d06d66d008070231d2b8bfae
|
3 |
+
size 4692673952
|
OpenMath2-Llama3.1-8B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e123625cbabea478652244689f5a262a5104d48674bc4f08faf8ca883da56a1e
|
3 |
+
size 5599298976
|
OpenMath2-Llama3.1-8B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768a1abbd0f42a20e22788da46d392bae5347607d7726c91d5ea14e7380b1dc8
|
3 |
+
size 5732992416
|
OpenMath2-Llama3.1-8B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81d9aab28a6125cc2d2803d085079b83c366639654b4713434dad388ac731fdf
|
3 |
+
size 5599298976
|
OpenMath2-Llama3.1-8B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7376e398da4f918651349861a1c42abf78731ddd692428ffdbc9baa6fa3d1747
|
3 |
+
size 6596011424
|
OpenMath2-Llama3.1-8B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17da94e769a5fd6f6a8ad45c44f6cd3fb9ca9c4038ab822d4edfa64b8e92c6c
|
3 |
+
size 8540775840
|
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3.1
|
3 |
+
base_model: nvidia/OpenMath2-Llama3.1-8B
|
4 |
+
datasets:
|
5 |
+
- nvidia/OpenMathInstruct-2
|
6 |
+
language:
|
7 |
+
- en
|
8 |
+
tags:
|
9 |
+
- nvidia
|
10 |
+
- math
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
library_name: transformers
|
14 |
+
---
|
15 |
+
|
16 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
17 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
18 |
+
</div>
|
19 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
20 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
21 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
22 |
+
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>
|
23 |
+
</p>
|
24 |
+
</div>
|
25 |
+
</div>
|
26 |
+
|
27 |
+
## nvidia/OpenMath2-Llama3.1-8B - GGUF
|
28 |
+
|
29 |
+
This repo contains GGUF format model files for [nvidia/OpenMath2-Llama3.1-8B](https://huggingface.co/nvidia/OpenMath2-Llama3.1-8B).
|
30 |
+
|
31 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit ec7f3ac](https://github.com/ggerganov/llama.cpp/commit/ec7f3ac9ab33e46b136eb5ab6a76c4d81f57c7f1).
|
32 |
+
|
33 |
+
<div style="text-align: left; margin: 20px 0;">
|
34 |
+
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
35 |
+
Run them on the TensorBlock client using your local machine ↗
|
36 |
+
</a>
|
37 |
+
</div>
|
38 |
+
|
39 |
+
## Prompt template
|
40 |
+
|
41 |
+
```
|
42 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
43 |
+
|
44 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
45 |
+
|
46 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
47 |
+
```
|
48 |
+
|
49 |
+
## Model file specification
|
50 |
+
|
51 |
+
| Filename | Quant type | File Size | Description |
|
52 |
+
| -------- | ---------- | --------- | ----------- |
|
53 |
+
| [OpenMath2-Llama3.1-8B-Q2_K.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
54 |
+
| [OpenMath2-Llama3.1-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
|
55 |
+
| [OpenMath2-Llama3.1-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
56 |
+
| [OpenMath2-Llama3.1-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
57 |
+
| [OpenMath2-Llama3.1-8B-Q4_0.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
58 |
+
| [OpenMath2-Llama3.1-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
59 |
+
| [OpenMath2-Llama3.1-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
60 |
+
| [OpenMath2-Llama3.1-8B-Q5_0.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
61 |
+
| [OpenMath2-Llama3.1-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
62 |
+
| [OpenMath2-Llama3.1-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
63 |
+
| [OpenMath2-Llama3.1-8B-Q6_K.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
64 |
+
| [OpenMath2-Llama3.1-8B-Q8_0.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-8B-GGUF/blob/main/OpenMath2-Llama3.1-8B-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
65 |
+
|
66 |
+
|
67 |
+
## Downloading instruction
|
68 |
+
|
69 |
+
### Command line
|
70 |
+
|
71 |
+
Firstly, install Huggingface Client
|
72 |
+
|
73 |
+
```shell
|
74 |
+
pip install -U "huggingface_hub[cli]"
|
75 |
+
```
|
76 |
+
|
77 |
+
Then, downoad the individual model file the a local directory
|
78 |
+
|
79 |
+
```shell
|
80 |
+
huggingface-cli download tensorblock/OpenMath2-Llama3.1-8B-GGUF --include "OpenMath2-Llama3.1-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
81 |
+
```
|
82 |
+
|
83 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
84 |
+
|
85 |
+
```shell
|
86 |
+
huggingface-cli download tensorblock/OpenMath2-Llama3.1-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
87 |
+
```
|