Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +78 -0
- dictalm2.0-instruct-Q2_K.gguf +3 -0
- dictalm2.0-instruct-Q3_K_L.gguf +3 -0
- dictalm2.0-instruct-Q3_K_M.gguf +3 -0
- dictalm2.0-instruct-Q3_K_S.gguf +3 -0
- dictalm2.0-instruct-Q4_0.gguf +3 -0
- dictalm2.0-instruct-Q4_K_M.gguf +3 -0
- dictalm2.0-instruct-Q4_K_S.gguf +3 -0
- dictalm2.0-instruct-Q5_0.gguf +3 -0
- dictalm2.0-instruct-Q5_K_M.gguf +3 -0
- dictalm2.0-instruct-Q5_K_S.gguf +3 -0
- dictalm2.0-instruct-Q6_K.gguf +3 -0
- dictalm2.0-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 |
+
dictalm2.0-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
dictalm2.0-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
dictalm2.0-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
dictalm2.0-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
dictalm2.0-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
dictalm2.0-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
dictalm2.0-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
dictalm2.0-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
dictalm2.0-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
dictalm2.0-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
dictalm2.0-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
dictalm2.0-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
- he
|
7 |
+
tags:
|
8 |
+
- instruction-tuned
|
9 |
+
- TensorBlock
|
10 |
+
- GGUF
|
11 |
+
base_model: dicta-il/dictalm2.0-instruct
|
12 |
+
inference:
|
13 |
+
parameters:
|
14 |
+
temperature: 0.7
|
15 |
+
---
|
16 |
+
|
17 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
18 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
19 |
+
</div>
|
20 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
21 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
22 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
23 |
+
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>
|
24 |
+
</p>
|
25 |
+
</div>
|
26 |
+
</div>
|
27 |
+
|
28 |
+
## dicta-il/dictalm2.0-instruct - GGUF
|
29 |
+
|
30 |
+
This repo contains GGUF format model files for [dicta-il/dictalm2.0-instruct](https://huggingface.co/dicta-il/dictalm2.0-instruct).
|
31 |
+
|
32 |
+
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).
|
33 |
+
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
<s>[INST] {prompt} [/INST]
|
38 |
+
```
|
39 |
+
|
40 |
+
## Model file specification
|
41 |
+
|
42 |
+
| Filename | Quant type | File Size | Description |
|
43 |
+
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [dictalm2.0-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q2_K.gguf) | Q2_K | 2.538 GB | smallest, significant quality loss - not recommended for most purposes |
|
45 |
+
| [dictalm2.0-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q3_K_S.gguf) | Q3_K_S | 2.953 GB | very small, high quality loss |
|
46 |
+
| [dictalm2.0-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q3_K_M.gguf) | Q3_K_M | 3.283 GB | very small, high quality loss |
|
47 |
+
| [dictalm2.0-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q3_K_L.gguf) | Q3_K_L | 3.565 GB | small, substantial quality loss |
|
48 |
+
| [dictalm2.0-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q4_0.gguf) | Q4_0 | 3.833 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
49 |
+
| [dictalm2.0-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q4_K_S.gguf) | Q4_K_S | 3.862 GB | small, greater quality loss |
|
50 |
+
| [dictalm2.0-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q4_K_M.gguf) | Q4_K_M | 4.075 GB | medium, balanced quality - recommended |
|
51 |
+
| [dictalm2.0-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q5_0.gguf) | Q5_0 | 4.661 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
52 |
+
| [dictalm2.0-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q5_K_S.gguf) | Q5_K_S | 4.661 GB | large, low quality loss - recommended |
|
53 |
+
| [dictalm2.0-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q5_K_M.gguf) | Q5_K_M | 4.786 GB | large, very low quality loss - recommended |
|
54 |
+
| [dictalm2.0-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q6_K.gguf) | Q6_K | 5.541 GB | very large, extremely low quality loss |
|
55 |
+
| [dictalm2.0-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/dictalm2.0-instruct-GGUF/tree/main/dictalm2.0-instruct-Q8_0.gguf) | Q8_0 | 7.177 GB | very large, extremely low quality loss - not recommended |
|
56 |
+
|
57 |
+
|
58 |
+
## Downloading instruction
|
59 |
+
|
60 |
+
### Command line
|
61 |
+
|
62 |
+
Firstly, install Huggingface Client
|
63 |
+
|
64 |
+
```shell
|
65 |
+
pip install -U "huggingface_hub[cli]"
|
66 |
+
```
|
67 |
+
|
68 |
+
Then, downoad the individual model file the a local directory
|
69 |
+
|
70 |
+
```shell
|
71 |
+
huggingface-cli download tensorblock/dictalm2.0-instruct-GGUF --include "dictalm2.0-instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
72 |
+
```
|
73 |
+
|
74 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
75 |
+
|
76 |
+
```shell
|
77 |
+
huggingface-cli download tensorblock/dictalm2.0-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
78 |
+
```
|
dictalm2.0-instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a4a58be4adcf5f5bdda7406f7d4d8c23343b01623aa3256b9f2605a237c86ae
|
3 |
+
size 2724689536
|
dictalm2.0-instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfae7e2163f974dbbb6b618fb4aee503a5a01ccdaa9fe5f95e4f6883b981672f
|
3 |
+
size 3827951232
|
dictalm2.0-instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1db3ccf3b43b015ac9153445fed3f8c029997c7f464f0559ade8110dc572b2da
|
3 |
+
size 3524912768
|
dictalm2.0-instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c18cdf34b8b2e57154a7a0b1ff1103752bd27e769e5e3d0bfe53856378f12a4
|
3 |
+
size 3170494080
|
dictalm2.0-instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e657f311b75c1cefb51bc8533c717657c8cadd5c63ddbeca442992600b9beef5
|
3 |
+
size 4115469952
|
dictalm2.0-instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecf8daee65bdd5c2331fdd982664a24e85f406400dc407ffeb4e5c2d2f38f59f
|
3 |
+
size 4374992512
|
dictalm2.0-instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cc99b3362da1bef2f3522b829f190ae68117393fb9078e78a1effa549d4173a
|
3 |
+
size 4146927232
|
dictalm2.0-instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97a1b87abae326d5597ce5ac841e529d8599e68339c4a748f3565d6100e11789
|
3 |
+
size 5004859008
|
dictalm2.0-instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a0881e5cd6c0b762cde023c1a731f726a298abd9f70d44bbc24ff7be3f4eda
|
3 |
+
size 5138552448
|
dictalm2.0-instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:575b6584686d60a48a4894857dfe6d52a331893890080ba7f44ca3e36aba8f32
|
3 |
+
size 5004859008
|
dictalm2.0-instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7efeef5b8a6c6b9443f7ccd96b23da75c6dfd29e5f7cbf368741a1adf9a957ce
|
3 |
+
size 5949834880
|
dictalm2.0-instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b77fb6d759965b6d30371b26199f05b587492dc1eb4b252db1078c51ab3e4017
|
3 |
+
size 7705912960
|