Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +82 -0
- mhm-7b-v1.3-Q2_K.gguf +3 -0
- mhm-7b-v1.3-Q3_K_L.gguf +3 -0
- mhm-7b-v1.3-Q3_K_M.gguf +3 -0
- mhm-7b-v1.3-Q3_K_S.gguf +3 -0
- mhm-7b-v1.3-Q4_0.gguf +3 -0
- mhm-7b-v1.3-Q4_K_M.gguf +3 -0
- mhm-7b-v1.3-Q4_K_S.gguf +3 -0
- mhm-7b-v1.3-Q5_0.gguf +3 -0
- mhm-7b-v1.3-Q5_K_M.gguf +3 -0
- mhm-7b-v1.3-Q5_K_S.gguf +3 -0
- mhm-7b-v1.3-Q6_K.gguf +3 -0
- mhm-7b-v1.3-Q8_0.gguf +3 -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 |
+
mhm-7b-v1.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
mhm-7b-v1.3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
mhm-7b-v1.3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
mhm-7b-v1.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
mhm-7b-v1.3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
mhm-7b-v1.3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
mhm-7b-v1.3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
mhm-7b-v1.3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
mhm-7b-v1.3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
mhm-7b-v1.3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
mhm-7b-v1.3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
mhm-7b-v1.3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- moe
|
4 |
+
- merge
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
license: apache-2.0
|
8 |
+
base_model: h2m/mhm-7b-v1.3
|
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 |
+
## h2m/mhm-7b-v1.3 - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [h2m/mhm-7b-v1.3](https://huggingface.co/h2m/mhm-7b-v1.3).
|
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 |
+
<|im_start|>system
|
38 |
+
{system_prompt}<|im_end|>
|
39 |
+
<|im_start|>user
|
40 |
+
{prompt}<|im_end|>
|
41 |
+
<|im_start|>assistant
|
42 |
+
```
|
43 |
+
|
44 |
+
## Model file specification
|
45 |
+
|
46 |
+
| Filename | Quant type | File Size | Description |
|
47 |
+
| -------- | ---------- | --------- | ----------- |
|
48 |
+
| [mhm-7b-v1.3-Q2_K.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
|
49 |
+
| [mhm-7b-v1.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss |
|
50 |
+
| [mhm-7b-v1.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss |
|
51 |
+
| [mhm-7b-v1.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss |
|
52 |
+
| [mhm-7b-v1.3-Q4_0.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
53 |
+
| [mhm-7b-v1.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss |
|
54 |
+
| [mhm-7b-v1.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
|
55 |
+
| [mhm-7b-v1.3-Q5_0.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
56 |
+
| [mhm-7b-v1.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
|
57 |
+
| [mhm-7b-v1.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
|
58 |
+
| [mhm-7b-v1.3-Q6_K.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss |
|
59 |
+
| [mhm-7b-v1.3-Q8_0.gguf](https://huggingface.co/tensorblock/mhm-7b-v1.3-GGUF/blob/main/mhm-7b-v1.3-Q8_0.gguf) | Q8_0 | 7.696 GB | very large, extremely low quality loss - not recommended |
|
60 |
+
|
61 |
+
|
62 |
+
## Downloading instruction
|
63 |
+
|
64 |
+
### Command line
|
65 |
+
|
66 |
+
Firstly, install Huggingface Client
|
67 |
+
|
68 |
+
```shell
|
69 |
+
pip install -U "huggingface_hub[cli]"
|
70 |
+
```
|
71 |
+
|
72 |
+
Then, downoad the individual model file the a local directory
|
73 |
+
|
74 |
+
```shell
|
75 |
+
huggingface-cli download tensorblock/mhm-7b-v1.3-GGUF --include "mhm-7b-v1.3-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
76 |
+
```
|
77 |
+
|
78 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
79 |
+
|
80 |
+
```shell
|
81 |
+
huggingface-cli download tensorblock/mhm-7b-v1.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
82 |
+
```
|
mhm-7b-v1.3-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87bcac5d49ab0f38366cde20995324d027669337f8d36f64bcd893b0eb8b91fc
|
3 |
+
size 2719242528
|
mhm-7b-v1.3-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85f168f3796643c20a904d343480224f111bf36712edd35a3bbca6dcb1305ff9
|
3 |
+
size 3822024992
|
mhm-7b-v1.3-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768d11b598870760158ed100d118928bd46a4e5c6e132f3c3a20278f8a693d21
|
3 |
+
size 3518986528
|
mhm-7b-v1.3-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe3a8cd4123a845bba014d53f83e5b3c5c7bc6692cff06cda7b4ad1d858bf661
|
3 |
+
size 3164567840
|
mhm-7b-v1.3-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:299eda2565af88d87d8cf82ec6b61333554c6fb4e9235a98eb188e47c768c364
|
3 |
+
size 4108917024
|
mhm-7b-v1.3-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1db8c678de213d8ac92a9130b8b9817601e9a21395ecd2a466a0f05b24c2b9e1
|
3 |
+
size 4368439584
|
mhm-7b-v1.3-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b8e50bfea229d6904923670e1bcf9f3b0527ba745e24dac02412ac0a92a3bee
|
3 |
+
size 4140374304
|
mhm-7b-v1.3-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b463ac7de4a1715a66e83883239433c07b3cfbbe5f235087ab14b5cdb52240f
|
3 |
+
size 4997716256
|
mhm-7b-v1.3-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09e2e8ba2c97ac00f7f07e4b8069994e597907323f5c2a64a7aa83cbd8459af5
|
3 |
+
size 5131409696
|
mhm-7b-v1.3-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cf5b0be708ef0ea747971e47838d22d36077c81bf9728e6114c5ae9a955b0b6
|
3 |
+
size 4997716256
|
mhm-7b-v1.3-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46207486c188d32864e13d8d0ecba894f9c783f892eed10ae5152cf10560ea07
|
3 |
+
size 5942065440
|
mhm-7b-v1.3-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6781d6e32b78d638b05b73918f46142635dc86d4d08d7d48e67f63b8163e215f
|
3 |
+
size 7695857952
|