Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- CodeLlama-34B-Instruct-fp16-Q2_K.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q3_K_L.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q3_K_M.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q3_K_S.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q4_0.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q4_K_M.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q4_K_S.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q5_0.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q5_K_M.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q5_K_S.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q6_K.gguf +3 -0
- CodeLlama-34B-Instruct-fp16-Q8_0.gguf +3 -0
- README.md +72 -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-34B-Instruct-fp16-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
CodeLlama-34B-Instruct-fp16-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
CodeLlama-34B-Instruct-fp16-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
CodeLlama-34B-Instruct-fp16-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
CodeLlama-34B-Instruct-fp16-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
CodeLlama-34B-Instruct-fp16-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
CodeLlama-34B-Instruct-fp16-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
CodeLlama-34B-Instruct-fp16-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
CodeLlama-34B-Instruct-fp16-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
CodeLlama-34B-Instruct-fp16-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
CodeLlama-34B-Instruct-fp16-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
CodeLlama-34B-Instruct-fp16-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
CodeLlama-34B-Instruct-fp16-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e280ca7a8a663ec79957b4eb3a5c24a83bb237b5400aae6ef7c7bef926263fc2
|
3 |
+
size 12505690752
|
CodeLlama-34B-Instruct-fp16-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acd42035d496f3956dd8c6dde0933197028400df853e4bf1411954e4368a8ea1
|
3 |
+
size 17771524736
|
CodeLlama-34B-Instruct-fp16-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e7b2490e675e9ccc719dc6bf38253e256f2968669a379fd0705ec6c7c0ff217
|
3 |
+
size 16306139776
|
CodeLlama-34B-Instruct-fp16-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d71b09ea924eb452ca29bde71baa69e286f954aa288b590d52f146ae83064a2f
|
3 |
+
size 14605349504
|
CodeLlama-34B-Instruct-fp16-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bbab61a94e89fc0e5c2407f47fdf3a5e1c1f1835365b4406448fa60674bf5a9
|
3 |
+
size 19052049024
|
CodeLlama-34B-Instruct-fp16-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f88022d60e8c9176917b5320c411a5611dd2ef9dd130812cf1b9556cf70bf5c6
|
3 |
+
size 20219900544
|
CodeLlama-34B-Instruct-fp16-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c84d5c05dd08a912996b0a84c8e09b5724ca7c0fe60d84e8d014a0b9eab46c7d
|
3 |
+
size 19191509632
|
CodeLlama-34B-Instruct-fp16-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6c003e0d4b66ee14aef89c8659cabf3174756286856d4600d42c3ab4e263f84
|
3 |
+
size 23237177984
|
CodeLlama-34B-Instruct-fp16-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27621f484cf8b32d8a15517bb17fa668874b5b314279d1211ac4a3595f583921
|
3 |
+
size 23838798464
|
CodeLlama-34B-Instruct-fp16-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c603e527619a6cb8a8c8f83ece8b7b9191abcb424f84fd580feb4cdf92cee0
|
3 |
+
size 23237177984
|
CodeLlama-34B-Instruct-fp16-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79132b68fef342860041476556bc46ded10ad60b17692fe9e6d96548e18bb7e2
|
3 |
+
size 27683877504
|
CodeLlama-34B-Instruct-fp16-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9eb20d2d3a59a1ce8c6dd69dc81020daddac821bc6f1aa6887c4c5d073ce006c
|
3 |
+
size 35856052864
|
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
tags:
|
4 |
+
- llama-2
|
5 |
+
- codellama
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
base_model: TheBloke/CodeLlama-34B-Instruct-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-34B-Instruct-fp16 - GGUF
|
23 |
+
|
24 |
+
This repo contains GGUF format model files for [TheBloke/CodeLlama-34B-Instruct-fp16](https://huggingface.co/TheBloke/CodeLlama-34B-Instruct-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 |
+
## Prompt template
|
29 |
+
|
30 |
+
```
|
31 |
+
|
32 |
+
```
|
33 |
+
|
34 |
+
## Model file specification
|
35 |
+
|
36 |
+
| Filename | Quant type | File Size | Description |
|
37 |
+
| -------- | ---------- | --------- | ----------- |
|
38 |
+
| [CodeLlama-34B-Instruct-fp16-Q2_K.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q2_K.gguf) | Q2_K | 11.647 GB | smallest, significant quality loss - not recommended for most purposes |
|
39 |
+
| [CodeLlama-34B-Instruct-fp16-Q3_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q3_K_S.gguf) | Q3_K_S | 13.602 GB | very small, high quality loss |
|
40 |
+
| [CodeLlama-34B-Instruct-fp16-Q3_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q3_K_M.gguf) | Q3_K_M | 15.186 GB | very small, high quality loss |
|
41 |
+
| [CodeLlama-34B-Instruct-fp16-Q3_K_L.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q3_K_L.gguf) | Q3_K_L | 16.551 GB | small, substantial quality loss |
|
42 |
+
| [CodeLlama-34B-Instruct-fp16-Q4_0.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q4_0.gguf) | Q4_0 | 17.744 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
43 |
+
| [CodeLlama-34B-Instruct-fp16-Q4_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q4_K_S.gguf) | Q4_K_S | 17.873 GB | small, greater quality loss |
|
44 |
+
| [CodeLlama-34B-Instruct-fp16-Q4_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q4_K_M.gguf) | Q4_K_M | 18.831 GB | medium, balanced quality - recommended |
|
45 |
+
| [CodeLlama-34B-Instruct-fp16-Q5_0.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q5_0.gguf) | Q5_0 | 21.641 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
46 |
+
| [CodeLlama-34B-Instruct-fp16-Q5_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q5_K_S.gguf) | Q5_K_S | 21.641 GB | large, low quality loss - recommended |
|
47 |
+
| [CodeLlama-34B-Instruct-fp16-Q5_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q5_K_M.gguf) | Q5_K_M | 22.202 GB | large, very low quality loss - recommended |
|
48 |
+
| [CodeLlama-34B-Instruct-fp16-Q6_K.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q6_K.gguf) | Q6_K | 25.783 GB | very large, extremely low quality loss |
|
49 |
+
| [CodeLlama-34B-Instruct-fp16-Q8_0.gguf](https://huggingface.co/tensorblock/CodeLlama-34B-Instruct-fp16-GGUF/tree/main/CodeLlama-34B-Instruct-fp16-Q8_0.gguf) | Q8_0 | 33.394 GB | very large, extremely low quality loss - not recommended |
|
50 |
+
|
51 |
+
|
52 |
+
## Downloading instruction
|
53 |
+
|
54 |
+
### Command line
|
55 |
+
|
56 |
+
Firstly, install Huggingface Client
|
57 |
+
|
58 |
+
```shell
|
59 |
+
pip install -U "huggingface_hub[cli]"
|
60 |
+
```
|
61 |
+
|
62 |
+
Then, downoad the individual model file the a local directory
|
63 |
+
|
64 |
+
```shell
|
65 |
+
huggingface-cli download tensorblock/CodeLlama-34B-Instruct-fp16-GGUF --include "CodeLlama-34B-Instruct-fp16-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
66 |
+
```
|
67 |
+
|
68 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
69 |
+
|
70 |
+
```shell
|
71 |
+
huggingface-cli download tensorblock/CodeLlama-34B-Instruct-fp16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
72 |
+
```
|