Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- AceInstruct-7B-Q2_K.gguf +3 -0
- AceInstruct-7B-Q3_K_L.gguf +3 -0
- AceInstruct-7B-Q3_K_M.gguf +3 -0
- AceInstruct-7B-Q3_K_S.gguf +3 -0
- AceInstruct-7B-Q4_0.gguf +3 -0
- AceInstruct-7B-Q4_K_M.gguf +3 -0
- AceInstruct-7B-Q4_K_S.gguf +3 -0
- AceInstruct-7B-Q5_0.gguf +3 -0
- AceInstruct-7B-Q5_K_M.gguf +3 -0
- AceInstruct-7B-Q5_K_S.gguf +3 -0
- AceInstruct-7B-Q6_K.gguf +3 -0
- AceInstruct-7B-Q8_0.gguf +3 -0
- README.md +90 -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 |
+
AceInstruct-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
AceInstruct-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
AceInstruct-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
AceInstruct-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
AceInstruct-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
AceInstruct-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
AceInstruct-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
AceInstruct-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
AceInstruct-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
AceInstruct-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
AceInstruct-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
AceInstruct-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
AceInstruct-7B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0df989d0456e1ef2a20d536a7e46ac0f73f1411b24995c39397b18c402e6395a
|
3 |
+
size 3015937952
|
AceInstruct-7B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96533456162162aa7699bbd9cf335a73196af2634a0096d0d5103bf35b2ef52b
|
3 |
+
size 4088457120
|
AceInstruct-7B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ded36585b9abfb97a15c80779fa3ee8cb38dcb8a71fc0547e763957a2fdd97cc
|
3 |
+
size 3808389024
|
AceInstruct-7B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb0c952d851949cf962a0dd9dde7a5974e632908461fb1a92dabcdff063e5447
|
3 |
+
size 3492366240
|
AceInstruct-7B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e45fcb31de8f04d7f1053108d5de77808741096f239ceaade4e79a40387aa1db
|
3 |
+
size 4431388576
|
AceInstruct-7B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0490d50e6a94c6145451af19956fef990d9ac66d0c009ed863c87caf60afd98
|
3 |
+
size 4683071392
|
AceInstruct-7B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b6eeb1e87bc3066adba2aadda9393336d6b84f64a191474245c620e6fd61944
|
3 |
+
size 4457766816
|
AceInstruct-7B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57761cb537675d10f656b4c2fe891af38121343d59acb88b0d61d8e71c7fa2c0
|
3 |
+
size 5315174304
|
AceInstruct-7B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd80d09f13f7f7e78b2b4fbb3d71fb9aa3e9031dfd69ee84b76f0d6c7833de23
|
3 |
+
size 5444829088
|
AceInstruct-7B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e4c6fb875898666541463269e368b18c25f70618cb232af653c846ee38bc3e3
|
3 |
+
size 5315174304
|
AceInstruct-7B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7888a9ffa8240b05ae6a4be642c108678984b8652e8936b160cbcf58040f1af
|
3 |
+
size 6254196640
|
AceInstruct-7B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c24b20930e4be5458c5d42f0e5c1ee1d000839419ba2ff2167badd1f6f12a39
|
3 |
+
size 8098523040
|
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
tags:
|
7 |
+
- nvidia
|
8 |
+
- AceInstruct
|
9 |
+
- code
|
10 |
+
- math
|
11 |
+
- general_domain
|
12 |
+
- instruct_model
|
13 |
+
- pytorch
|
14 |
+
- TensorBlock
|
15 |
+
- GGUF
|
16 |
+
base_model: nvidia/AceInstruct-7B
|
17 |
+
---
|
18 |
+
|
19 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
20 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
21 |
+
</div>
|
22 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
23 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
24 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
25 |
+
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>
|
26 |
+
</p>
|
27 |
+
</div>
|
28 |
+
</div>
|
29 |
+
|
30 |
+
## nvidia/AceInstruct-7B - GGUF
|
31 |
+
|
32 |
+
This repo contains GGUF format model files for [nvidia/AceInstruct-7B](https://huggingface.co/nvidia/AceInstruct-7B).
|
33 |
+
|
34 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
|
35 |
+
|
36 |
+
<div style="text-align: left; margin: 20px 0;">
|
37 |
+
<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;">
|
38 |
+
Run them on the TensorBlock client using your local machine ↗
|
39 |
+
</a>
|
40 |
+
</div>
|
41 |
+
|
42 |
+
## Prompt template
|
43 |
+
|
44 |
+
```
|
45 |
+
<|im_start|>system
|
46 |
+
{system_prompt}<|im_end|>
|
47 |
+
<|im_start|>user
|
48 |
+
{prompt}<|im_end|>
|
49 |
+
<|im_start|>assistant
|
50 |
+
```
|
51 |
+
|
52 |
+
## Model file specification
|
53 |
+
|
54 |
+
| Filename | Quant type | File Size | Description |
|
55 |
+
| -------- | ---------- | --------- | ----------- |
|
56 |
+
| [AceInstruct-7B-Q2_K.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q2_K.gguf) | Q2_K | 3.016 GB | smallest, significant quality loss - not recommended for most purposes |
|
57 |
+
| [AceInstruct-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q3_K_S.gguf) | Q3_K_S | 3.492 GB | very small, high quality loss |
|
58 |
+
| [AceInstruct-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q3_K_M.gguf) | Q3_K_M | 3.808 GB | very small, high quality loss |
|
59 |
+
| [AceInstruct-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q3_K_L.gguf) | Q3_K_L | 4.088 GB | small, substantial quality loss |
|
60 |
+
| [AceInstruct-7B-Q4_0.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q4_0.gguf) | Q4_0 | 4.431 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
61 |
+
| [AceInstruct-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q4_K_S.gguf) | Q4_K_S | 4.458 GB | small, greater quality loss |
|
62 |
+
| [AceInstruct-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q4_K_M.gguf) | Q4_K_M | 4.683 GB | medium, balanced quality - recommended |
|
63 |
+
| [AceInstruct-7B-Q5_0.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q5_0.gguf) | Q5_0 | 5.315 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
64 |
+
| [AceInstruct-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q5_K_S.gguf) | Q5_K_S | 5.315 GB | large, low quality loss - recommended |
|
65 |
+
| [AceInstruct-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q5_K_M.gguf) | Q5_K_M | 5.445 GB | large, very low quality loss - recommended |
|
66 |
+
| [AceInstruct-7B-Q6_K.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q6_K.gguf) | Q6_K | 6.254 GB | very large, extremely low quality loss |
|
67 |
+
| [AceInstruct-7B-Q8_0.gguf](https://huggingface.co/tensorblock/AceInstruct-7B-GGUF/blob/main/AceInstruct-7B-Q8_0.gguf) | Q8_0 | 8.099 GB | very large, extremely low quality loss - not recommended |
|
68 |
+
|
69 |
+
|
70 |
+
## Downloading instruction
|
71 |
+
|
72 |
+
### Command line
|
73 |
+
|
74 |
+
Firstly, install Huggingface Client
|
75 |
+
|
76 |
+
```shell
|
77 |
+
pip install -U "huggingface_hub[cli]"
|
78 |
+
```
|
79 |
+
|
80 |
+
Then, downoad the individual model file the a local directory
|
81 |
+
|
82 |
+
```shell
|
83 |
+
huggingface-cli download tensorblock/AceInstruct-7B-GGUF --include "AceInstruct-7B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
84 |
+
```
|
85 |
+
|
86 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
87 |
+
|
88 |
+
```shell
|
89 |
+
huggingface-cli download tensorblock/AceInstruct-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
90 |
+
```
|