Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q2_K.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_L.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_M.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_S.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q4_0.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_M.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_S.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q5_0.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_M.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_S.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q6_K.gguf +3 -0
- ELYZA-japanese-CodeLlama-7b-instruct-Q8_0.gguf +3 -0
- README.md +79 -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 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
ELYZA-japanese-CodeLlama-7b-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
ELYZA-japanese-CodeLlama-7b-instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29c2fb83736da0728748fe605738dd25a1b107762b959b1654c48e8586f6857e
|
3 |
+
size 2532939968
|
ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da35c6852a6b487c4f3dc4cab9996d978c9fc768257d6ae0da1a31d73c6f3e3
|
3 |
+
size 3597193920
|
ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe11e365d2e54b84f2da326f3e88eb9bd9d246c9cd06c8485f5a2d6ecdd44698
|
3 |
+
size 3298087616
|
ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50a4afd6ce72e73cf65754db2b4aa374d65486dcf1fd2ea669c0807392919b32
|
3 |
+
size 2948387520
|
ELYZA-japanese-CodeLlama-7b-instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f9e7ca21e6c73bc84a434883656579457b34804b16a3417c31c89d8509e7a10
|
3 |
+
size 3825898688
|
ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df36e7946cbe6ece1955da11ae417afa34bca42ab0b14a3f9dea9e871efc9f03
|
3 |
+
size 4081095872
|
ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47b8a377a53470060c124086e1d18d358d72dedd0759d252fcd03803433669f
|
3 |
+
size 3856831680
|
ELYZA-japanese-CodeLlama-7b-instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f28b4be2f4169b502ed7959608c7761096a069c784c8d6f4e166579ee1ebaa7c
|
3 |
+
size 4651791552
|
ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29ef99dab5d6b61526e2e7b2531aab22cf3428e9e06ab9ea5019f40e656b8210
|
3 |
+
size 4783256768
|
ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76968dcd935228cb5f54ee9c9cc4ec0ab9071852fb6a07f5a477a4230adf8dd2
|
3 |
+
size 4651791552
|
ELYZA-japanese-CodeLlama-7b-instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:520c6b8370168ef857e60b53d4a30f6e97898663904b7564b04060476e94da76
|
3 |
+
size 5529302720
|
ELYZA-japanese-CodeLlama-7b-instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4086ee3fa36d385d1114b19916d50f2165489ba2b0d6461eee125d2c328473df
|
3 |
+
size 7161230016
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
language:
|
4 |
+
- ja
|
5 |
+
- en
|
6 |
+
base_model: elyza/ELYZA-japanese-CodeLlama-7b-instruct
|
7 |
+
tags:
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
---
|
11 |
+
|
12 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
13 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
14 |
+
</div>
|
15 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
16 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
17 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
18 |
+
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>
|
19 |
+
</p>
|
20 |
+
</div>
|
21 |
+
</div>
|
22 |
+
|
23 |
+
## elyza/ELYZA-japanese-CodeLlama-7b-instruct - GGUF
|
24 |
+
|
25 |
+
This repo contains GGUF format model files for [elyza/ELYZA-japanese-CodeLlama-7b-instruct](https://huggingface.co/elyza/ELYZA-japanese-CodeLlama-7b-instruct).
|
26 |
+
|
27 |
+
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).
|
28 |
+
|
29 |
+
<div style="text-align: left; margin: 20px 0;">
|
30 |
+
<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;">
|
31 |
+
Run them on the TensorBlock client using your local machine ↗
|
32 |
+
</a>
|
33 |
+
</div>
|
34 |
+
|
35 |
+
## Prompt template
|
36 |
+
|
37 |
+
```
|
38 |
+
|
39 |
+
```
|
40 |
+
|
41 |
+
## Model file specification
|
42 |
+
|
43 |
+
| Filename | Quant type | File Size | Description |
|
44 |
+
| -------- | ---------- | --------- | ----------- |
|
45 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_S.gguf) | Q3_K_S | 2.948 GB | very small, high quality loss |
|
47 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_M.gguf) | Q3_K_M | 3.298 GB | very small, high quality loss |
|
48 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q3_K_L.gguf) | Q3_K_L | 3.597 GB | small, substantial quality loss |
|
49 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q4_0.gguf) | Q4_0 | 3.826 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_S.gguf) | Q4_K_S | 3.857 GB | small, greater quality loss |
|
51 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q4_K_M.gguf) | Q4_K_M | 4.081 GB | medium, balanced quality - recommended |
|
52 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q5_0.gguf) | Q5_0 | 4.652 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_S.gguf) | Q5_K_S | 4.652 GB | large, low quality loss - recommended |
|
54 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q5_K_M.gguf) | Q5_K_M | 4.783 GB | large, very low quality loss - recommended |
|
55 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q6_K.gguf) | Q6_K | 5.529 GB | very large, extremely low quality loss |
|
56 |
+
| [ELYZA-japanese-CodeLlama-7b-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF/blob/main/ELYZA-japanese-CodeLlama-7b-instruct-Q8_0.gguf) | Q8_0 | 7.161 GB | very large, extremely low quality loss - not recommended |
|
57 |
+
|
58 |
+
|
59 |
+
## Downloading instruction
|
60 |
+
|
61 |
+
### Command line
|
62 |
+
|
63 |
+
Firstly, install Huggingface Client
|
64 |
+
|
65 |
+
```shell
|
66 |
+
pip install -U "huggingface_hub[cli]"
|
67 |
+
```
|
68 |
+
|
69 |
+
Then, downoad the individual model file the a local directory
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF --include "ELYZA-japanese-CodeLlama-7b-instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
73 |
+
```
|
74 |
+
|
75 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/ELYZA-japanese-CodeLlama-7b-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
79 |
+
```
|