Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +74 -0
- dictalm2-it-qa-fine-tune-Q2_K.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q3_K_L.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q3_K_M.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q3_K_S.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q4_0.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q4_K_M.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q4_K_S.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q5_0.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q5_K_M.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q5_K_S.gguf +3 -0
- dictalm2-it-qa-fine-tune-Q6_K.gguf +3 -0
- dictalm2-it-qa-fine-tune-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-it-qa-fine-tune-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
dictalm2-it-qa-fine-tune-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
dictalm2-it-qa-fine-tune-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
dictalm2-it-qa-fine-tune-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
dictalm2-it-qa-fine-tune-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
dictalm2-it-qa-fine-tune-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
dictalm2-it-qa-fine-tune-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
dictalm2-it-qa-fine-tune-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
dictalm2-it-qa-fine-tune-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
dictalm2-it-qa-fine-tune-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
dictalm2-it-qa-fine-tune-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
dictalm2-it-qa-fine-tune-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
base_model: 618AI/dictalm2-it-qa-fine-tune
|
4 |
+
license: apache-2.0
|
5 |
+
language:
|
6 |
+
- he
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
tags:
|
9 |
+
- TensorBlock
|
10 |
+
- GGUF
|
11 |
+
---
|
12 |
+
|
13 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
14 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
15 |
+
</div>
|
16 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
17 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
18 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
19 |
+
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>
|
20 |
+
</p>
|
21 |
+
</div>
|
22 |
+
</div>
|
23 |
+
|
24 |
+
## 618AI/dictalm2-it-qa-fine-tune - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [618AI/dictalm2-it-qa-fine-tune](https://huggingface.co/618AI/dictalm2-it-qa-fine-tune).
|
27 |
+
|
28 |
+
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).
|
29 |
+
|
30 |
+
## Prompt template
|
31 |
+
|
32 |
+
```
|
33 |
+
<s>[INST] {prompt} [/INST]
|
34 |
+
```
|
35 |
+
|
36 |
+
## Model file specification
|
37 |
+
|
38 |
+
| Filename | Quant type | File Size | Description |
|
39 |
+
| -------- | ---------- | --------- | ----------- |
|
40 |
+
| [dictalm2-it-qa-fine-tune-Q2_K.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q2_K.gguf) | Q2_K | 2.538 GB | smallest, significant quality loss - not recommended for most purposes |
|
41 |
+
| [dictalm2-it-qa-fine-tune-Q3_K_S.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q3_K_S.gguf) | Q3_K_S | 2.953 GB | very small, high quality loss |
|
42 |
+
| [dictalm2-it-qa-fine-tune-Q3_K_M.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q3_K_M.gguf) | Q3_K_M | 3.283 GB | very small, high quality loss |
|
43 |
+
| [dictalm2-it-qa-fine-tune-Q3_K_L.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q3_K_L.gguf) | Q3_K_L | 3.565 GB | small, substantial quality loss |
|
44 |
+
| [dictalm2-it-qa-fine-tune-Q4_0.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q4_0.gguf) | Q4_0 | 3.833 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
45 |
+
| [dictalm2-it-qa-fine-tune-Q4_K_S.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q4_K_S.gguf) | Q4_K_S | 3.862 GB | small, greater quality loss |
|
46 |
+
| [dictalm2-it-qa-fine-tune-Q4_K_M.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q4_K_M.gguf) | Q4_K_M | 4.075 GB | medium, balanced quality - recommended |
|
47 |
+
| [dictalm2-it-qa-fine-tune-Q5_0.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q5_0.gguf) | Q5_0 | 4.661 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
48 |
+
| [dictalm2-it-qa-fine-tune-Q5_K_S.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q5_K_S.gguf) | Q5_K_S | 4.661 GB | large, low quality loss - recommended |
|
49 |
+
| [dictalm2-it-qa-fine-tune-Q5_K_M.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q5_K_M.gguf) | Q5_K_M | 4.786 GB | large, very low quality loss - recommended |
|
50 |
+
| [dictalm2-it-qa-fine-tune-Q6_K.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q6_K.gguf) | Q6_K | 5.541 GB | very large, extremely low quality loss |
|
51 |
+
| [dictalm2-it-qa-fine-tune-Q8_0.gguf](https://huggingface.co/tensorblock/dictalm2-it-qa-fine-tune-GGUF/tree/main/dictalm2-it-qa-fine-tune-Q8_0.gguf) | Q8_0 | 7.177 GB | very large, extremely low quality loss - not recommended |
|
52 |
+
|
53 |
+
|
54 |
+
## Downloading instruction
|
55 |
+
|
56 |
+
### Command line
|
57 |
+
|
58 |
+
Firstly, install Huggingface Client
|
59 |
+
|
60 |
+
```shell
|
61 |
+
pip install -U "huggingface_hub[cli]"
|
62 |
+
```
|
63 |
+
|
64 |
+
Then, downoad the individual model file the a local directory
|
65 |
+
|
66 |
+
```shell
|
67 |
+
huggingface-cli download tensorblock/dictalm2-it-qa-fine-tune-GGUF --include "dictalm2-it-qa-fine-tune-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
68 |
+
```
|
69 |
+
|
70 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
71 |
+
|
72 |
+
```shell
|
73 |
+
huggingface-cli download tensorblock/dictalm2-it-qa-fine-tune-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
74 |
+
```
|
dictalm2-it-qa-fine-tune-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d50e460bd4227033b9f60808f24afe4bfed2a31752a7f54860e4f976de6d009b
|
3 |
+
size 2724694304
|
dictalm2-it-qa-fine-tune-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6675a3bb4404e366f99d0035d639194bae9ed7d25b8c1c8a2ce13c1600095181
|
3 |
+
size 3827956416
|
dictalm2-it-qa-fine-tune-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0199eb56ed2f6023173195978ed6fcbc9b65e3a7d2379e466b15d9d580b480d3
|
3 |
+
size 3524917952
|
dictalm2-it-qa-fine-tune-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c31d465209038d9c99e3853c3ab4edb5dc9a8c071df36f59965d5f9c16c938de
|
3 |
+
size 3170499264
|
dictalm2-it-qa-fine-tune-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a42dc874c06157dbd05e9e74de267ef6820c2502d5e0cf4cb8d86966d6a7e5c
|
3 |
+
size 4115475680
|
dictalm2-it-qa-fine-tune-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf1951c2bc4c81676d6356e77db8fe25ce7bc3555a3554353cf7f3f4860d4b0
|
3 |
+
size 4374998240
|
dictalm2-it-qa-fine-tune-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:221d56193ac595d4b020bf796c89d74d494cbfe173cdc1cadeabe25675905b2c
|
3 |
+
size 4146932960
|
dictalm2-it-qa-fine-tune-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78450eb9c71500ef7ec5c780fe5e7f3913df39f94387395815dfb9734f39e583
|
3 |
+
size 5004865248
|
dictalm2-it-qa-fine-tune-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a941b381fdc2ffef59674e019c1df9f742f86c3d64b4d50ca95907a2f4c0696
|
3 |
+
size 5138558688
|
dictalm2-it-qa-fine-tune-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2cc11371734d5aa8edd30d1894789af298101f6f1d73759718126a6a3ee055b
|
3 |
+
size 5004865248
|
dictalm2-it-qa-fine-tune-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e1aba1b9987c5cad4d42499cf918025133731cea837ffa38eeee7132410e50d
|
3 |
+
size 5949841664
|
dictalm2-it-qa-fine-tune-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8877288841d980901ccbbf13093ec29d25b1e5d86dc466725edb33ad39649ba2
|
3 |
+
size 7705921728
|