Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- CodeLlama-13b-hf-Q2_K.gguf +3 -0
- CodeLlama-13b-hf-Q3_K_L.gguf +3 -0
- CodeLlama-13b-hf-Q3_K_M.gguf +3 -0
- CodeLlama-13b-hf-Q3_K_S.gguf +3 -0
- CodeLlama-13b-hf-Q4_0.gguf +3 -0
- CodeLlama-13b-hf-Q4_K_M.gguf +3 -0
- CodeLlama-13b-hf-Q4_K_S.gguf +3 -0
- CodeLlama-13b-hf-Q5_0.gguf +3 -0
- CodeLlama-13b-hf-Q5_K_M.gguf +3 -0
- CodeLlama-13b-hf-Q5_K_S.gguf +3 -0
- CodeLlama-13b-hf-Q6_K.gguf +3 -0
- CodeLlama-13b-hf-Q8_0.gguf +3 -0
- README.md +74 -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 |
+
CodeLlama-13b-hf-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
CodeLlama-13b-hf-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
CodeLlama-13b-hf-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
CodeLlama-13b-hf-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
CodeLlama-13b-hf-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
CodeLlama-13b-hf-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
CodeLlama-13b-hf-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
CodeLlama-13b-hf-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
CodeLlama-13b-hf-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
CodeLlama-13b-hf-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
CodeLlama-13b-hf-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
CodeLlama-13b-hf-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
CodeLlama-13b-hf-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e258144f328c32187815c0ce2d63f10fb94133886c46ce892104010c049cfcf
|
3 |
+
size 4854364960
|
CodeLlama-13b-hf-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f558482daffd7bbb125934ae1c2770c26ce47cdece462ab1068f100b28bb2b3
|
3 |
+
size 6929662880
|
CodeLlama-13b-hf-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13aed6a96aeb38397d6a7a3a84c55782fae3bb9d72d3d8d05f0d3341c2602f7b
|
3 |
+
size 6337872800
|
CodeLlama-13b-hf-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb234961623b7b1a56da7f14638dfa0cdbe53e746d005c2cf96dc10b3e213d10
|
3 |
+
size 5659083680
|
CodeLlama-13b-hf-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e24d656f37cee6a7fbe66b7326a4540722a85b73695a906cbd88882244e4497d
|
3 |
+
size 7365948960
|
CodeLlama-13b-hf-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5052e898232a54923c0afb693ec923b8c1350a79011ce7e3bb80451346669182
|
3 |
+
size 7866070560
|
CodeLlama-13b-hf-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:427d197d380218524a2deefd750e82205cadd6a7768bdf2f247eba414b4e2b83
|
3 |
+
size 7423292960
|
CodeLlama-13b-hf-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1aca930e896bc0e43fabce6b29ddb45bc518b7f095d82617548cc1b0d2dd65d
|
3 |
+
size 8972410400
|
CodeLlama-13b-hf-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e94701d510034c87f63cb7bca53ec0cb81e263c02cbcb100800eea8656d6626f
|
3 |
+
size 9230048800
|
CodeLlama-13b-hf-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3babf92cf7f2c572d21c3ebd00daeb16edaf48dde5b1d0be4cf2a4b425b5d308
|
3 |
+
size 8972410400
|
CodeLlama-13b-hf-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0541c205269ccb6d52fb93fb582b115b3abeb1b7139066001ca45bef6471471
|
3 |
+
size 10679275680
|
CodeLlama-13b-hf-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:191a6648ff0f6376f112e64fd2956394f3b340e9a71598d3d4a43fd7d9b1b827
|
3 |
+
size 13831494560
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- code
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- llama-2
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
license: llama2
|
10 |
+
base_model: codellama/CodeLlama-13b-hf
|
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 |
+
## codellama/CodeLlama-13b-hf - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf).
|
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 |
+
|
34 |
+
```
|
35 |
+
|
36 |
+
## Model file specification
|
37 |
+
|
38 |
+
| Filename | Quant type | File Size | Description |
|
39 |
+
| -------- | ---------- | --------- | ----------- |
|
40 |
+
| [CodeLlama-13b-hf-Q2_K.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q2_K.gguf) | Q2_K | 4.521 GB | smallest, significant quality loss - not recommended for most purposes |
|
41 |
+
| [CodeLlama-13b-hf-Q3_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q3_K_S.gguf) | Q3_K_S | 5.270 GB | very small, high quality loss |
|
42 |
+
| [CodeLlama-13b-hf-Q3_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q3_K_M.gguf) | Q3_K_M | 5.903 GB | very small, high quality loss |
|
43 |
+
| [CodeLlama-13b-hf-Q3_K_L.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q3_K_L.gguf) | Q3_K_L | 6.454 GB | small, substantial quality loss |
|
44 |
+
| [CodeLlama-13b-hf-Q4_0.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q4_0.gguf) | Q4_0 | 6.860 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
45 |
+
| [CodeLlama-13b-hf-Q4_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q4_K_S.gguf) | Q4_K_S | 6.913 GB | small, greater quality loss |
|
46 |
+
| [CodeLlama-13b-hf-Q4_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q4_K_M.gguf) | Q4_K_M | 7.326 GB | medium, balanced quality - recommended |
|
47 |
+
| [CodeLlama-13b-hf-Q5_0.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q5_0.gguf) | Q5_0 | 8.356 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
48 |
+
| [CodeLlama-13b-hf-Q5_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q5_K_S.gguf) | Q5_K_S | 8.356 GB | large, low quality loss - recommended |
|
49 |
+
| [CodeLlama-13b-hf-Q5_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q5_K_M.gguf) | Q5_K_M | 8.596 GB | large, very low quality loss - recommended |
|
50 |
+
| [CodeLlama-13b-hf-Q6_K.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q6_K.gguf) | Q6_K | 9.946 GB | very large, extremely low quality loss |
|
51 |
+
| [CodeLlama-13b-hf-Q8_0.gguf](https://huggingface.co/tensorblock/CodeLlama-13b-hf-GGUF/tree/main/CodeLlama-13b-hf-Q8_0.gguf) | Q8_0 | 12.882 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/CodeLlama-13b-hf-GGUF --include "CodeLlama-13b-hf-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/CodeLlama-13b-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
74 |
+
```
|