Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +81 -0
- granite-7b-lab-Q2_K.gguf +3 -0
- granite-7b-lab-Q3_K_L.gguf +3 -0
- granite-7b-lab-Q3_K_M.gguf +3 -0
- granite-7b-lab-Q3_K_S.gguf +3 -0
- granite-7b-lab-Q4_0.gguf +3 -0
- granite-7b-lab-Q4_K_M.gguf +3 -0
- granite-7b-lab-Q4_K_S.gguf +3 -0
- granite-7b-lab-Q5_0.gguf +3 -0
- granite-7b-lab-Q5_K_M.gguf +3 -0
- granite-7b-lab-Q5_K_S.gguf +3 -0
- granite-7b-lab-Q6_K.gguf +3 -0
- granite-7b-lab-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 |
+
granite-7b-lab-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
granite-7b-lab-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
granite-7b-lab-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
granite-7b-lab-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
granite-7b-lab-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
granite-7b-lab-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
granite-7b-lab-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
granite-7b-lab-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
granite-7b-lab-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
granite-7b-lab-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
granite-7b-lab-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
granite-7b-lab-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: text-generation
|
3 |
+
tags:
|
4 |
+
- granite
|
5 |
+
- ibm
|
6 |
+
- lab
|
7 |
+
- labrador
|
8 |
+
- labradorite
|
9 |
+
- TensorBlock
|
10 |
+
- GGUF
|
11 |
+
license: apache-2.0
|
12 |
+
language:
|
13 |
+
- en
|
14 |
+
base_model: instructlab/granite-7b-lab
|
15 |
+
---
|
16 |
+
|
17 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
18 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
19 |
+
</div>
|
20 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
21 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
22 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
23 |
+
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>
|
24 |
+
</p>
|
25 |
+
</div>
|
26 |
+
</div>
|
27 |
+
|
28 |
+
## instructlab/granite-7b-lab - GGUF
|
29 |
+
|
30 |
+
This repo contains GGUF format model files for [instructlab/granite-7b-lab](https://huggingface.co/instructlab/granite-7b-lab).
|
31 |
+
|
32 |
+
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).
|
33 |
+
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
<|system|>
|
38 |
+
{system_prompt}
|
39 |
+
<|user|>
|
40 |
+
{prompt}
|
41 |
+
```
|
42 |
+
|
43 |
+
## Model file specification
|
44 |
+
|
45 |
+
| Filename | Quant type | File Size | Description |
|
46 |
+
| -------- | ---------- | --------- | ----------- |
|
47 |
+
| [granite-7b-lab-Q2_K.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q2_K.gguf) | Q2_K | 2.359 GB | smallest, significant quality loss - not recommended for most purposes |
|
48 |
+
| [granite-7b-lab-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q3_K_S.gguf) | Q3_K_S | 2.746 GB | very small, high quality loss |
|
49 |
+
| [granite-7b-lab-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q3_K_M.gguf) | Q3_K_M | 3.072 GB | very small, high quality loss |
|
50 |
+
| [granite-7b-lab-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q3_K_L.gguf) | Q3_K_L | 3.350 GB | small, substantial quality loss |
|
51 |
+
| [granite-7b-lab-Q4_0.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q4_0.gguf) | Q4_0 | 3.563 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
52 |
+
| [granite-7b-lab-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q4_K_S.gguf) | Q4_K_S | 3.592 GB | small, greater quality loss |
|
53 |
+
| [granite-7b-lab-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q4_K_M.gguf) | Q4_K_M | 3.801 GB | medium, balanced quality - recommended |
|
54 |
+
| [granite-7b-lab-Q5_0.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q5_0.gguf) | Q5_0 | 4.332 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
55 |
+
| [granite-7b-lab-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q5_K_S.gguf) | Q5_K_S | 4.332 GB | large, low quality loss - recommended |
|
56 |
+
| [granite-7b-lab-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q5_K_M.gguf) | Q5_K_M | 4.455 GB | large, very low quality loss - recommended |
|
57 |
+
| [granite-7b-lab-Q6_K.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q6_K.gguf) | Q6_K | 5.150 GB | very large, extremely low quality loss |
|
58 |
+
| [granite-7b-lab-Q8_0.gguf](https://huggingface.co/tensorblock/granite-7b-lab-GGUF/tree/main/granite-7b-lab-Q8_0.gguf) | Q8_0 | 6.669 GB | very large, extremely low quality loss - not recommended |
|
59 |
+
|
60 |
+
|
61 |
+
## Downloading instruction
|
62 |
+
|
63 |
+
### Command line
|
64 |
+
|
65 |
+
Firstly, install Huggingface Client
|
66 |
+
|
67 |
+
```shell
|
68 |
+
pip install -U "huggingface_hub[cli]"
|
69 |
+
```
|
70 |
+
|
71 |
+
Then, downoad the individual model file the a local directory
|
72 |
+
|
73 |
+
```shell
|
74 |
+
huggingface-cli download tensorblock/granite-7b-lab-GGUF --include "granite-7b-lab-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
75 |
+
```
|
76 |
+
|
77 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
78 |
+
|
79 |
+
```shell
|
80 |
+
huggingface-cli download tensorblock/granite-7b-lab-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
81 |
+
```
|
granite-7b-lab-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e01f416ff0ef68f501cba031ae9edf2acdda29854e94e48fd798d7ff6d7188f8
|
3 |
+
size 2532902816
|
granite-7b-lab-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c24e0d90e53c6019f1d69e4d3f8b02725eb09ab8a992be554fe0cb0072e5b4b
|
3 |
+
size 3597153440
|
granite-7b-lab-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5fd7b771238d3db5ae6acfb152f1941ee415fec1284fb5bb40ac7f608178a1a
|
3 |
+
size 3298047136
|
granite-7b-lab-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6791ba9dff35a3c51c10384d5bc9fbd6239bf9dd59b31e8cd055aa187373b96
|
3 |
+
size 2948347040
|
granite-7b-lab-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:126aa98504e721aa6a70dcbd673666fee096beb6fb1a9fdae1ba264deb452dfc
|
3 |
+
size 3825853856
|
granite-7b-lab-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1827da81267b603e8a980dfc743edb6173d23e0b7a54edcc2780aa418bc5c12d
|
3 |
+
size 4081051040
|
granite-7b-lab-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a90f2e32d4c6fb8343a685c856f274ee012dd3cf3a196eb9513ed968a4ef890c
|
3 |
+
size 3856786848
|
granite-7b-lab-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8a4dbf3a2664b0da973e8c1eb465d4b5c864ccb9ad290a91c773a6a0b836231
|
3 |
+
size 4651742624
|
granite-7b-lab-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc5b758a8e7279e0e0dddc46aeabeda6f9af363f40d4e5e74362c3ae7fe081e0
|
3 |
+
size 4783207840
|
granite-7b-lab-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00b52505de38f383efdef3e0a90379330159c7d6e1ce2bd359883fa0153fa45e
|
3 |
+
size 4651742624
|
granite-7b-lab-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e4b7848661cb37e9f23cb00574ac5dbc17167afcba11c7f49452c56dba409e4
|
3 |
+
size 5529249440
|
granite-7b-lab-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c38e9008786a261fc39deb62c3451619dc540642a42d15b1a5e88fbf71343d10
|
3 |
+
size 7161160864
|