Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Mistral-7B-Instruct-IPO-Q2_K.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q3_K_L.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q3_K_M.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q3_K_S.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q4_0.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q4_K_M.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q4_K_S.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q5_0.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q5_K_M.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q5_K_S.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q6_K.gguf +3 -0
- Mistral-7B-Instruct-IPO-Q8_0.gguf +3 -0
- README.md +71 -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 |
+
Mistral-7B-Instruct-IPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Mistral-7B-Instruct-IPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Mistral-7B-Instruct-IPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Mistral-7B-Instruct-IPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Mistral-7B-Instruct-IPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Mistral-7B-Instruct-IPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Mistral-7B-Instruct-IPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Mistral-7B-Instruct-IPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Mistral-7B-Instruct-IPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Mistral-7B-Instruct-IPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Mistral-7B-Instruct-IPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Mistral-7B-Instruct-IPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Mistral-7B-Instruct-IPO-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0a11522e4776d0a0d517039dd8d40de6cf645413dc803b536fcd15ed984bb63
|
3 |
+
size 2719242912
|
Mistral-7B-Instruct-IPO-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:095e40eb919dbdd771299f4cd4cc586b9741f531e625e0daa8218ac130762d0e
|
3 |
+
size 3822025376
|
Mistral-7B-Instruct-IPO-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:187e142ac8590efdc37052ec0a337ae33355faf4c7fff110a5f2f9675fe463fa
|
3 |
+
size 3518986912
|
Mistral-7B-Instruct-IPO-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb7bf300bee77230d9562b98a468da4fc740bdc4a10369f3e041c8de01f25681
|
3 |
+
size 3164568224
|
Mistral-7B-Instruct-IPO-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfea45218212640855fb8b8562cd8018953e1fe488375f7082eccf832e855115
|
3 |
+
size 4108917408
|
Mistral-7B-Instruct-IPO-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c68e1aa0c18554aa2e4bb2a6d5b91d4e3f0142d74f51ab2619ee98f409956d2d
|
3 |
+
size 4368439968
|
Mistral-7B-Instruct-IPO-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc232267c470e98230fd4815c56541befbe74a52db9f5c52cfc790554a8beaf8
|
3 |
+
size 4140374688
|
Mistral-7B-Instruct-IPO-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4ad7a8cf0083425f8ada93b492a558a650d722bc6903102a68df8a922815f2f
|
3 |
+
size 4997716640
|
Mistral-7B-Instruct-IPO-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3bfc3b3e5eafc6de90bd9b33515e1d69b3292ceeac971db2dc25a5759bba457
|
3 |
+
size 5131410080
|
Mistral-7B-Instruct-IPO-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16b99d46e96e1dedbb77254ef0c4165793423a96dac037fe02c83cae85f513e7
|
3 |
+
size 4997716640
|
Mistral-7B-Instruct-IPO-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0fcfbf2701595cd171417748dcd1ecd45082343791b957be4d805f27ad50783
|
3 |
+
size 5942065824
|
Mistral-7B-Instruct-IPO-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85db2a19dcd48fca0293760949f5f2c0cb5da47d55c7ca7bec5973dfcb70408c
|
3 |
+
size 7695858336
|
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: princeton-nlp/Mistral-7B-Instruct-IPO
|
3 |
+
tags:
|
4 |
+
- TensorBlock
|
5 |
+
- GGUF
|
6 |
+
---
|
7 |
+
|
8 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
9 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
10 |
+
</div>
|
11 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
12 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
13 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
14 |
+
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>
|
15 |
+
</p>
|
16 |
+
</div>
|
17 |
+
</div>
|
18 |
+
|
19 |
+
## princeton-nlp/Mistral-7B-Instruct-IPO - GGUF
|
20 |
+
|
21 |
+
This repo contains GGUF format model files for [princeton-nlp/Mistral-7B-Instruct-IPO](https://huggingface.co/princeton-nlp/Mistral-7B-Instruct-IPO).
|
22 |
+
|
23 |
+
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).
|
24 |
+
|
25 |
+
## Prompt template
|
26 |
+
|
27 |
+
```
|
28 |
+
[INST] {system_prompt}
|
29 |
+
|
30 |
+
{prompt} [/INST]
|
31 |
+
```
|
32 |
+
|
33 |
+
## Model file specification
|
34 |
+
|
35 |
+
| Filename | Quant type | File Size | Description |
|
36 |
+
| -------- | ---------- | --------- | ----------- |
|
37 |
+
| [Mistral-7B-Instruct-IPO-Q2_K.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
|
38 |
+
| [Mistral-7B-Instruct-IPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
|
39 |
+
| [Mistral-7B-Instruct-IPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
|
40 |
+
| [Mistral-7B-Instruct-IPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
|
41 |
+
| [Mistral-7B-Instruct-IPO-Q4_0.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
42 |
+
| [Mistral-7B-Instruct-IPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
|
43 |
+
| [Mistral-7B-Instruct-IPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
|
44 |
+
| [Mistral-7B-Instruct-IPO-Q5_0.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
45 |
+
| [Mistral-7B-Instruct-IPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
|
46 |
+
| [Mistral-7B-Instruct-IPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
|
47 |
+
| [Mistral-7B-Instruct-IPO-Q6_K.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
|
48 |
+
| [Mistral-7B-Instruct-IPO-Q8_0.gguf](https://huggingface.co/tensorblock/Mistral-7B-Instruct-IPO-GGUF/tree/main/Mistral-7B-Instruct-IPO-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
|
49 |
+
|
50 |
+
|
51 |
+
## Downloading instruction
|
52 |
+
|
53 |
+
### Command line
|
54 |
+
|
55 |
+
Firstly, install Huggingface Client
|
56 |
+
|
57 |
+
```shell
|
58 |
+
pip install -U "huggingface_hub[cli]"
|
59 |
+
```
|
60 |
+
|
61 |
+
Then, downoad the individual model file the a local directory
|
62 |
+
|
63 |
+
```shell
|
64 |
+
huggingface-cli download tensorblock/Mistral-7B-Instruct-IPO-GGUF --include "Mistral-7B-Instruct-IPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
65 |
+
```
|
66 |
+
|
67 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
68 |
+
|
69 |
+
```shell
|
70 |
+
huggingface-cli download tensorblock/Mistral-7B-Instruct-IPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
71 |
+
```
|