morriszms commited on
Commit
1110f74
·
verified ·
1 Parent(s): d85362e

Upload folder using huggingface_hub

Browse files
.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
+ vistral-7b-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ vistral-7b-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ vistral-7b-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ vistral-7b-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ vistral-7b-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ vistral-7b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ vistral-7b-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ vistral-7b-chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ vistral-7b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ vistral-7b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ vistral-7b-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ vistral-7b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - vi
4
+ library_name: transformers
5
+ tags:
6
+ - LLMs
7
+ - NLP
8
+ - Vietnamese
9
+ - Large Language Models
10
+ - TensorBlock
11
+ - GGUF
12
+ license: afl-3.0
13
+ extra_gated_prompt: You agree not to use the model for experiments that could harm
14
+ human subjects.
15
+ extra_gated_fields:
16
+ Name: text
17
+ Email: text
18
+ Affiliation: text
19
+ Country: text
20
+ I agree to the LICENSE of this model: checkbox
21
+ base_model: minhtt/vistral-7b-chat
22
+ ---
23
+
24
+ <div style="width: auto; margin-left: auto; margin-right: auto">
25
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
26
+ </div>
27
+ <div style="display: flex; justify-content: space-between; width: 100%;">
28
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
29
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
30
+ 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>
31
+ </p>
32
+ </div>
33
+ </div>
34
+
35
+ ## minhtt/vistral-7b-chat - GGUF
36
+
37
+ This repo contains GGUF format model files for [minhtt/vistral-7b-chat](https://huggingface.co/minhtt/vistral-7b-chat).
38
+
39
+ 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).
40
+
41
+ <div style="text-align: left; margin: 20px 0;">
42
+ <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;">
43
+ Run them on the TensorBlock client using your local machine ↗
44
+ </a>
45
+ </div>
46
+
47
+ ## Prompt template
48
+
49
+ ```
50
+ <s>[INST] <<SYS>>
51
+ {system_prompt}
52
+ <</SYS>>
53
+
54
+ {prompt} [/INST]
55
+ ```
56
+
57
+ ## Model file specification
58
+
59
+ | Filename | Quant type | File Size | Description |
60
+ | -------- | ---------- | --------- | ----------- |
61
+ | [vistral-7b-chat-Q2_K.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q2_K.gguf) | Q2_K | 2.749 GB | smallest, significant quality loss - not recommended for most purposes |
62
+ | [vistral-7b-chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q3_K_S.gguf) | Q3_K_S | 3.197 GB | very small, high quality loss |
63
+ | [vistral-7b-chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q3_K_M.gguf) | Q3_K_M | 3.552 GB | very small, high quality loss |
64
+ | [vistral-7b-chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q3_K_L.gguf) | Q3_K_L | 3.855 GB | small, substantial quality loss |
65
+ | [vistral-7b-chat-Q4_0.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q4_0.gguf) | Q4_0 | 4.145 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
66
+ | [vistral-7b-chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q4_K_S.gguf) | Q4_K_S | 4.177 GB | small, greater quality loss |
67
+ | [vistral-7b-chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q4_K_M.gguf) | Q4_K_M | 4.405 GB | medium, balanced quality - recommended |
68
+ | [vistral-7b-chat-Q5_0.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q5_0.gguf) | Q5_0 | 5.037 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
69
+ | [vistral-7b-chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q5_K_S.gguf) | Q5_K_S | 5.037 GB | large, low quality loss - recommended |
70
+ | [vistral-7b-chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q5_K_M.gguf) | Q5_K_M | 5.171 GB | large, very low quality loss - recommended |
71
+ | [vistral-7b-chat-Q6_K.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q6_K.gguf) | Q6_K | 5.985 GB | very large, extremely low quality loss |
72
+ | [vistral-7b-chat-Q8_0.gguf](https://huggingface.co/tensorblock/vistral-7b-chat-GGUF/blob/main/vistral-7b-chat-Q8_0.gguf) | Q8_0 | 7.751 GB | very large, extremely low quality loss - not recommended |
73
+
74
+
75
+ ## Downloading instruction
76
+
77
+ ### Command line
78
+
79
+ Firstly, install Huggingface Client
80
+
81
+ ```shell
82
+ pip install -U "huggingface_hub[cli]"
83
+ ```
84
+
85
+ Then, downoad the individual model file the a local directory
86
+
87
+ ```shell
88
+ huggingface-cli download tensorblock/vistral-7b-chat-GGUF --include "vistral-7b-chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR
89
+ ```
90
+
91
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
92
+
93
+ ```shell
94
+ huggingface-cli download tensorblock/vistral-7b-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
95
+ ```
vistral-7b-chat-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56b502cc1f89018c81c2bc6380efad8b24d3dca88d0ce2bd347410d6862ca28
3
+ size 2749351168
vistral-7b-chat-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3508439970e6e75bcb8c055ec297c6f6824670a18ddd2ed4f84088c1f010f6
3
+ size 3854783136
vistral-7b-chat-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfda8b90b15a36ab19ce9cbfbc2a54786947d063086706ae2defc7a5421481b7
3
+ size 3551744672
vistral-7b-chat-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906f3b9526346d17dde8e8ab30bbe98b25c2fc820046bf8d5f0f3954bb4f8d21
3
+ size 3197325984
vistral-7b-chat-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42db081ec5ce834cfe26f1f4eb6b3823acca9e2371bafd6bd9c35205b01caa79
3
+ size 4145139904
vistral-7b-chat-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3bf118813e034ba64b04cc5a141cdc7ba58ecc7eb4b4da55e4494ea88011a3
3
+ size 4404662464
vistral-7b-chat-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7200acc782806934080b97d6599a68c1a8a902dda8e2e2c9262a2608666e442e
3
+ size 4176597184
vistral-7b-chat-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca6b192964fd8cfada73a0c43d1f2adfc9e2b97424d131cf9ace8810011805c
3
+ size 5037200064
vistral-7b-chat-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc8fe18d6064ecda8796af7a2891d5ddba5e642bbed1dab7f5182f426a228e2
3
+ size 5170893504
vistral-7b-chat-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a9b8757d922588cccc715ec41db15df2f4407287d294c28504d50b60e9552e
3
+ size 5037200064
vistral-7b-chat-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819a2189c41c06e738d5122b7ba5d1140e1175bd00601b3596c063c8ce88f612
3
+ size 5985013984
vistral-7b-chat-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dff17d61c4ec4b66a39e98dd98b698e42d834d835adbce8624744bd280961cf
3
+ size 7751442592