Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- CodeLlama-7B-fp16-Q2_K.gguf +3 -0
- CodeLlama-7B-fp16-Q3_K_L.gguf +3 -0
- CodeLlama-7B-fp16-Q3_K_M.gguf +3 -0
- CodeLlama-7B-fp16-Q3_K_S.gguf +3 -0
- CodeLlama-7B-fp16-Q4_0.gguf +3 -0
- CodeLlama-7B-fp16-Q4_K_M.gguf +3 -0
- CodeLlama-7B-fp16-Q4_K_S.gguf +3 -0
- CodeLlama-7B-fp16-Q5_0.gguf +3 -0
- CodeLlama-7B-fp16-Q5_K_M.gguf +3 -0
- CodeLlama-7B-fp16-Q5_K_S.gguf +3 -0
- CodeLlama-7B-fp16-Q6_K.gguf +3 -0
- CodeLlama-7B-fp16-Q8_0.gguf +3 -0
- README.md +78 -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-7B-fp16-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
CodeLlama-7B-fp16-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
CodeLlama-7B-fp16-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
CodeLlama-7B-fp16-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
CodeLlama-7B-fp16-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
CodeLlama-7B-fp16-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
CodeLlama-7B-fp16-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
CodeLlama-7B-fp16-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
CodeLlama-7B-fp16-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
CodeLlama-7B-fp16-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
CodeLlama-7B-fp16-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
CodeLlama-7B-fp16-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
CodeLlama-7B-fp16-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94dec610dd5c02c521e14a7c3a374af52b473ebaaa8687f9c71dffc734b62b47
|
3 |
+
size 2532939936
|
CodeLlama-7B-fp16-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:250e9949ff3d15534c857521d066f485f4615dd1bf94d87a135b182fa198e324
|
3 |
+
size 3597193888
|
CodeLlama-7B-fp16-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43f55b97421b3780a8224257d78bce98cd182118e680c08a4e5d3dbe9a5ff14b
|
3 |
+
size 3298087584
|
CodeLlama-7B-fp16-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:672dd4f6fe332b80c72fcd2450eac666e4b69c0461ad11ac5eb90dac1255f75f
|
3 |
+
size 2948387488
|
CodeLlama-7B-fp16-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e5202b5d69bd3bdd7012942b99f69188f43f608e3a9bad70e8ce965065ef10d
|
3 |
+
size 3825898656
|
CodeLlama-7B-fp16-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac82f47139c089ee1d317e15b0bf5a91bb02f3500281c67778aa0751b8ed64d7
|
3 |
+
size 4081095840
|
CodeLlama-7B-fp16-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:439c033e9ad472604687aa6521f3b341fec4d006b3c819d60292dbec93fe98f4
|
3 |
+
size 3856831648
|
CodeLlama-7B-fp16-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b90cde3906636a4daacaedc5bc646b8686669407deb8700081c86c9af2bd840
|
3 |
+
size 4651791520
|
CodeLlama-7B-fp16-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4fa852df8d1645dcebe050097d3afe7fcf9a7d9b9ec706edda207f57057391
|
3 |
+
size 4783256736
|
CodeLlama-7B-fp16-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5500e9f489e8f7c1e2a5f0433dce43428c6f4e106167a1866014dde538c2ee8
|
3 |
+
size 4651791520
|
CodeLlama-7B-fp16-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46c1c7b9273efd70936bf245be6bcf2f8c2ef0e0114b01228f52af011dcf3752
|
3 |
+
size 5529302688
|
CodeLlama-7B-fp16-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ee812945b5b84c4d7938107dbd53be9e6ea261df204b58ff3b5c63d423cdff3
|
3 |
+
size 7161229984
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
tags:
|
4 |
+
- llama-2
|
5 |
+
- codellama
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
base_model: TheBloke/CodeLlama-7B-fp16
|
9 |
+
---
|
10 |
+
|
11 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
12 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
13 |
+
</div>
|
14 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
15 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
16 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
17 |
+
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>
|
18 |
+
</p>
|
19 |
+
</div>
|
20 |
+
</div>
|
21 |
+
|
22 |
+
## TheBloke/CodeLlama-7B-fp16 - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [TheBloke/CodeLlama-7B-fp16](https://huggingface.co/TheBloke/CodeLlama-7B-fp16).
|
25 |
+
|
26 |
+
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).
|
27 |
+
|
28 |
+
<div style="text-align: left; margin: 20px 0;">
|
29 |
+
<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;">
|
30 |
+
Run them on the TensorBlock client using your local machine ↗
|
31 |
+
</a>
|
32 |
+
</div>
|
33 |
+
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
|
38 |
+
```
|
39 |
+
|
40 |
+
## Model file specification
|
41 |
+
|
42 |
+
| Filename | Quant type | File Size | Description |
|
43 |
+
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [CodeLlama-7B-fp16-Q2_K.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q2_K.gguf) | Q2_K | 2.359 GB | smallest, significant quality loss - not recommended for most purposes |
|
45 |
+
| [CodeLlama-7B-fp16-Q3_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q3_K_S.gguf) | Q3_K_S | 2.746 GB | very small, high quality loss |
|
46 |
+
| [CodeLlama-7B-fp16-Q3_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q3_K_M.gguf) | Q3_K_M | 3.072 GB | very small, high quality loss |
|
47 |
+
| [CodeLlama-7B-fp16-Q3_K_L.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q3_K_L.gguf) | Q3_K_L | 3.350 GB | small, substantial quality loss |
|
48 |
+
| [CodeLlama-7B-fp16-Q4_0.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q4_0.gguf) | Q4_0 | 3.563 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
49 |
+
| [CodeLlama-7B-fp16-Q4_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q4_K_S.gguf) | Q4_K_S | 3.592 GB | small, greater quality loss |
|
50 |
+
| [CodeLlama-7B-fp16-Q4_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q4_K_M.gguf) | Q4_K_M | 3.801 GB | medium, balanced quality - recommended |
|
51 |
+
| [CodeLlama-7B-fp16-Q5_0.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q5_0.gguf) | Q5_0 | 4.332 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
52 |
+
| [CodeLlama-7B-fp16-Q5_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q5_K_S.gguf) | Q5_K_S | 4.332 GB | large, low quality loss - recommended |
|
53 |
+
| [CodeLlama-7B-fp16-Q5_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q5_K_M.gguf) | Q5_K_M | 4.455 GB | large, very low quality loss - recommended |
|
54 |
+
| [CodeLlama-7B-fp16-Q6_K.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q6_K.gguf) | Q6_K | 5.150 GB | very large, extremely low quality loss |
|
55 |
+
| [CodeLlama-7B-fp16-Q8_0.gguf](https://huggingface.co/tensorblock/CodeLlama-7B-fp16-GGUF/blob/main/CodeLlama-7B-fp16-Q8_0.gguf) | Q8_0 | 6.669 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/CodeLlama-7B-fp16-GGUF --include "CodeLlama-7B-fp16-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/CodeLlama-7B-fp16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
78 |
+
```
|