Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- MetaModel_moe-Q2_K.gguf +3 -0
- MetaModel_moe-Q3_K_L.gguf +3 -0
- MetaModel_moe-Q3_K_M.gguf +3 -0
- MetaModel_moe-Q3_K_S.gguf +3 -0
- MetaModel_moe-Q4_0.gguf +3 -0
- MetaModel_moe-Q4_K_M.gguf +3 -0
- MetaModel_moe-Q4_K_S.gguf +3 -0
- MetaModel_moe-Q5_0.gguf +3 -0
- MetaModel_moe-Q5_K_M.gguf +3 -0
- MetaModel_moe-Q5_K_S.gguf +3 -0
- MetaModel_moe-Q6_K.gguf +3 -0
- MetaModel_moe-Q8_0.gguf +3 -0
- README.md +84 -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 |
+
MetaModel_moe-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
MetaModel_moe-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
MetaModel_moe-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
MetaModel_moe-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
MetaModel_moe-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
MetaModel_moe-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
MetaModel_moe-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
MetaModel_moe-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
MetaModel_moe-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
MetaModel_moe-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
MetaModel_moe-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
MetaModel_moe-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
MetaModel_moe-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afe196de57977f082cc27b5bd3f01a2cd7558c0a21ca2ab4b75056f73cb00f1d
|
3 |
+
size 13188763520
|
MetaModel_moe-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4b8d1d07adbfe39280a76eda14801d485c0aa60b0d5297d3bd2f7c1ac197903
|
3 |
+
size 18733838208
|
MetaModel_moe-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c775b1c9027787a03a6aa32805f7051f732c2aca2057a5a7d00df83cecd02edf
|
3 |
+
size 17287851904
|
MetaModel_moe-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9705c2150bd95b2ef44dd5d13242ef8fc3dd63bfbd5d6bfbd715bd618c11250a
|
3 |
+
size 15567662976
|
MetaModel_moe-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6073e597a5e57d328bcc34a0834b038402ca58e9b38eb0ab5a24eaf55d0d67ff
|
3 |
+
size 20344557440
|
MetaModel_moe-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b392e1c69c07147e0db81effe0423570e3001f93cc8ad5ccaac5ae6c6814ece
|
3 |
+
size 21823836032
|
MetaModel_moe-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:099e335bc3ee3281d5df42e6c435445c43424d5db720158a13bd9ce7c01a9d13
|
3 |
+
size 20522815360
|
MetaModel_moe-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06113262142162d4f825fa89411908281189bd1a4b60dd6456319af82fe6c404
|
3 |
+
size 24840458112
|
MetaModel_moe-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e5d8c90c947ad78ebf369be0720467ff1b62ff3fa89caa3ebff457e0b0b181a
|
3 |
+
size 25602510720
|
MetaModel_moe-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3e071b6f53f8cac3f7308da8bdeeb509057603fd26199213f3e269a5255d8e3
|
3 |
+
size 24840458112
|
MetaModel_moe-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab3f96b209761889b7b240dfc53c9674c9deaba973310735d2d7933ad318080a
|
3 |
+
size 29617352576
|
MetaModel_moe-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a07ce8946b7e6b0b0f9b141f41a5dfe3355bdec47fe3b6e8202935bb8397c86b
|
3 |
+
size 38359904128
|
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- mixtral
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
base_model: gagan3012/MetaModel_moe
|
9 |
+
---
|
10 |
+
|
11 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
12 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
13 |
+
</div>
|
14 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
15 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
16 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
17 |
+
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>
|
18 |
+
</p>
|
19 |
+
</div>
|
20 |
+
</div>
|
21 |
+
|
22 |
+
## gagan3012/MetaModel_moe - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [gagan3012/MetaModel_moe](https://huggingface.co/gagan3012/MetaModel_moe).
|
25 |
+
|
26 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
27 |
+
|
28 |
+
<div style="text-align: left; margin: 20px 0;">
|
29 |
+
<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;">
|
30 |
+
Run them on the TensorBlock client using your local machine ↗
|
31 |
+
</a>
|
32 |
+
</div>
|
33 |
+
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
### System:
|
38 |
+
{system_prompt}
|
39 |
+
|
40 |
+
### User:
|
41 |
+
{prompt}
|
42 |
+
|
43 |
+
### Assistant:
|
44 |
+
```
|
45 |
+
|
46 |
+
## Model file specification
|
47 |
+
|
48 |
+
| Filename | Quant type | File Size | Description |
|
49 |
+
| -------- | ---------- | --------- | ----------- |
|
50 |
+
| [MetaModel_moe-Q2_K.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q2_K.gguf) | Q2_K | 13.189 GB | smallest, significant quality loss - not recommended for most purposes |
|
51 |
+
| [MetaModel_moe-Q3_K_S.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q3_K_S.gguf) | Q3_K_S | 15.568 GB | very small, high quality loss |
|
52 |
+
| [MetaModel_moe-Q3_K_M.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q3_K_M.gguf) | Q3_K_M | 17.288 GB | very small, high quality loss |
|
53 |
+
| [MetaModel_moe-Q3_K_L.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q3_K_L.gguf) | Q3_K_L | 18.734 GB | small, substantial quality loss |
|
54 |
+
| [MetaModel_moe-Q4_0.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q4_0.gguf) | Q4_0 | 20.345 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
55 |
+
| [MetaModel_moe-Q4_K_S.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q4_K_S.gguf) | Q4_K_S | 20.523 GB | small, greater quality loss |
|
56 |
+
| [MetaModel_moe-Q4_K_M.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q4_K_M.gguf) | Q4_K_M | 21.824 GB | medium, balanced quality - recommended |
|
57 |
+
| [MetaModel_moe-Q5_0.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q5_0.gguf) | Q5_0 | 24.840 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
58 |
+
| [MetaModel_moe-Q5_K_S.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q5_K_S.gguf) | Q5_K_S | 24.840 GB | large, low quality loss - recommended |
|
59 |
+
| [MetaModel_moe-Q5_K_M.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q5_K_M.gguf) | Q5_K_M | 25.603 GB | large, very low quality loss - recommended |
|
60 |
+
| [MetaModel_moe-Q6_K.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q6_K.gguf) | Q6_K | 29.617 GB | very large, extremely low quality loss |
|
61 |
+
| [MetaModel_moe-Q8_0.gguf](https://huggingface.co/tensorblock/MetaModel_moe-GGUF/blob/main/MetaModel_moe-Q8_0.gguf) | Q8_0 | 38.360 GB | very large, extremely low quality loss - not recommended |
|
62 |
+
|
63 |
+
|
64 |
+
## Downloading instruction
|
65 |
+
|
66 |
+
### Command line
|
67 |
+
|
68 |
+
Firstly, install Huggingface Client
|
69 |
+
|
70 |
+
```shell
|
71 |
+
pip install -U "huggingface_hub[cli]"
|
72 |
+
```
|
73 |
+
|
74 |
+
Then, downoad the individual model file the a local directory
|
75 |
+
|
76 |
+
```shell
|
77 |
+
huggingface-cli download tensorblock/MetaModel_moe-GGUF --include "MetaModel_moe-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
78 |
+
```
|
79 |
+
|
80 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
81 |
+
|
82 |
+
```shell
|
83 |
+
huggingface-cli download tensorblock/MetaModel_moe-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
84 |
+
```
|