Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +107 -0
- TinyMistral-6x248M-Instruct-Q2_K.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q3_K_L.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q3_K_M.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q3_K_S.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q4_0.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q4_K_M.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q4_K_S.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q5_0.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q5_K_M.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q5_K_S.gguf +3 -0
- TinyMistral-6x248M-Instruct-Q6_K.gguf +3 -0
- TinyMistral-6x248M-Instruct-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 |
+
TinyMistral-6x248M-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
TinyMistral-6x248M-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
TinyMistral-6x248M-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
TinyMistral-6x248M-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
TinyMistral-6x248M-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
TinyMistral-6x248M-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
TinyMistral-6x248M-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
TinyMistral-6x248M-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
TinyMistral-6x248M-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
TinyMistral-6x248M-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
TinyMistral-6x248M-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
TinyMistral-6x248M-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- Locutusque/hercules-v1.0
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
base_model: M4-ai/TinyMistral-6x248M-Instruct
|
8 |
+
inference:
|
9 |
+
parameters:
|
10 |
+
do_sample: true
|
11 |
+
temperature: 0.2
|
12 |
+
top_p: 0.14
|
13 |
+
top_k: 12
|
14 |
+
max_new_tokens: 250
|
15 |
+
repetition_penalty: 1.1
|
16 |
+
widget:
|
17 |
+
- text: '<|im_start|>user
|
18 |
+
|
19 |
+
Write me a Python program that calculates the factorial of n. <|im_end|>
|
20 |
+
|
21 |
+
<|im_start|>assistant
|
22 |
+
|
23 |
+
'
|
24 |
+
- text: An emerging clinical approach to treat substance abuse disorders involves
|
25 |
+
a form of cognitive-behavioral therapy whereby addicts learn to reduce their reactivity
|
26 |
+
to drug-paired stimuli through cue-exposure or extinction training. It is, however,
|
27 |
+
- text: '<|im_start|>user
|
28 |
+
|
29 |
+
How do I say hello in Spanish? <|im_end|>
|
30 |
+
|
31 |
+
<|im_start|>assistant
|
32 |
+
|
33 |
+
'
|
34 |
+
tags:
|
35 |
+
- moe
|
36 |
+
- TensorBlock
|
37 |
+
- GGUF
|
38 |
+
---
|
39 |
+
|
40 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
41 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
42 |
+
</div>
|
43 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
44 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
45 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
46 |
+
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>
|
47 |
+
</p>
|
48 |
+
</div>
|
49 |
+
</div>
|
50 |
+
|
51 |
+
## M4-ai/TinyMistral-6x248M-Instruct - GGUF
|
52 |
+
|
53 |
+
This repo contains GGUF format model files for [M4-ai/TinyMistral-6x248M-Instruct](https://huggingface.co/M4-ai/TinyMistral-6x248M-Instruct).
|
54 |
+
|
55 |
+
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).
|
56 |
+
|
57 |
+
<div style="text-align: left; margin: 20px 0;">
|
58 |
+
<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;">
|
59 |
+
Run them on the TensorBlock client using your local machine ↗
|
60 |
+
</a>
|
61 |
+
</div>
|
62 |
+
|
63 |
+
## Prompt template
|
64 |
+
|
65 |
+
```
|
66 |
+
|
67 |
+
```
|
68 |
+
|
69 |
+
## Model file specification
|
70 |
+
|
71 |
+
| Filename | Quant type | File Size | Description |
|
72 |
+
| -------- | ---------- | --------- | ----------- |
|
73 |
+
| [TinyMistral-6x248M-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q2_K.gguf) | Q2_K | 0.379 GB | smallest, significant quality loss - not recommended for most purposes |
|
74 |
+
| [TinyMistral-6x248M-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.445 GB | very small, high quality loss |
|
75 |
+
| [TinyMistral-6x248M-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.487 GB | very small, high quality loss |
|
76 |
+
| [TinyMistral-6x248M-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.527 GB | small, substantial quality loss |
|
77 |
+
| [TinyMistral-6x248M-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q4_0.gguf) | Q4_0 | 0.574 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
78 |
+
| [TinyMistral-6x248M-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.577 GB | small, greater quality loss |
|
79 |
+
| [TinyMistral-6x248M-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.613 GB | medium, balanced quality - recommended |
|
80 |
+
| [TinyMistral-6x248M-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q5_0.gguf) | Q5_0 | 0.695 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
81 |
+
| [TinyMistral-6x248M-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q5_K_S.gguf) | Q5_K_S | 0.695 GB | large, low quality loss - recommended |
|
82 |
+
| [TinyMistral-6x248M-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q5_K_M.gguf) | Q5_K_M | 0.715 GB | large, very low quality loss - recommended |
|
83 |
+
| [TinyMistral-6x248M-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q6_K.gguf) | Q6_K | 0.824 GB | very large, extremely low quality loss |
|
84 |
+
| [TinyMistral-6x248M-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/TinyMistral-6x248M-Instruct-GGUF/blob/main/TinyMistral-6x248M-Instruct-Q8_0.gguf) | Q8_0 | 1.067 GB | very large, extremely low quality loss - not recommended |
|
85 |
+
|
86 |
+
|
87 |
+
## Downloading instruction
|
88 |
+
|
89 |
+
### Command line
|
90 |
+
|
91 |
+
Firstly, install Huggingface Client
|
92 |
+
|
93 |
+
```shell
|
94 |
+
pip install -U "huggingface_hub[cli]"
|
95 |
+
```
|
96 |
+
|
97 |
+
Then, downoad the individual model file the a local directory
|
98 |
+
|
99 |
+
```shell
|
100 |
+
huggingface-cli download tensorblock/TinyMistral-6x248M-Instruct-GGUF --include "TinyMistral-6x248M-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
101 |
+
```
|
102 |
+
|
103 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
104 |
+
|
105 |
+
```shell
|
106 |
+
huggingface-cli download tensorblock/TinyMistral-6x248M-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
107 |
+
```
|
TinyMistral-6x248M-Instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e2b41cf012cf913b85b83e97bd8ba555ac9f53d3e88a3a675b283437e4b3bf
|
3 |
+
size 379041152
|
TinyMistral-6x248M-Instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82b768e848841c6890210098c6bdf07f3ae73880e5b77d922831c771b572f056
|
3 |
+
size 526802816
|
TinyMistral-6x248M-Instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1beed18a5644e3b174787b2ed6a2db2c88010b5c05e34cc231c28af188f0d7d0
|
3 |
+
size 487153536
|
TinyMistral-6x248M-Instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b7b77e2ce093e0364c8e14c149dc3461bb5f70013f98eb0f9db83f9b500f72c
|
3 |
+
size 444891008
|
TinyMistral-6x248M-Instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39cb96544f6526430c2a963966725d1b9f7959c7b0d1662e963d2b04d42db9a9
|
3 |
+
size 573745696
|
TinyMistral-6x248M-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d33c2eb64ad0bfdfebe4e2eb41370133e776eb12a329d12d544670c0adb38774
|
3 |
+
size 613079584
|
TinyMistral-6x248M-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70847cf82eadbf6b18c150f324f18c0993f550bea6aaea74d10e9d19636830b5
|
3 |
+
size 577022496
|
TinyMistral-6x248M-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e04f6a84c4f118dde1b89a50838c45ad236148783cbdeb787bd77f252d8f7845
|
3 |
+
size 695020704
|
TinyMistral-6x248M-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da038436545c5a9513ca55f1a7495f1586c06bc71527358d919dd94c5e8529c0
|
3 |
+
size 715283616
|
TinyMistral-6x248M-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd753ae015dce81da6963adc5772d43ae54774d056cd59f8d5473f2de0e0485f
|
3 |
+
size 695020704
|
TinyMistral-6x248M-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d94737f99d011c87e993bdc3e1ddbf2b3bbd176f14b1eeb442319b4e831d939
|
3 |
+
size 823875424
|
TinyMistral-6x248M-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09d23bda55d30cabe9a7431c0b46a3560ca5655d3f122fa75430deab65904328
|
3 |
+
size 1066782944
|