Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +89 -0
- falcon-mamba-7b-instruct-Q2_K.gguf +3 -0
- falcon-mamba-7b-instruct-Q3_K_L.gguf +3 -0
- falcon-mamba-7b-instruct-Q3_K_M.gguf +3 -0
- falcon-mamba-7b-instruct-Q3_K_S.gguf +3 -0
- falcon-mamba-7b-instruct-Q4_0.gguf +3 -0
- falcon-mamba-7b-instruct-Q4_K_M.gguf +3 -0
- falcon-mamba-7b-instruct-Q4_K_S.gguf +3 -0
- falcon-mamba-7b-instruct-Q5_0.gguf +3 -0
- falcon-mamba-7b-instruct-Q5_K_M.gguf +3 -0
- falcon-mamba-7b-instruct-Q5_K_S.gguf +3 -0
- falcon-mamba-7b-instruct-Q6_K.gguf +3 -0
- falcon-mamba-7b-instruct-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 |
+
falcon-mamba-7b-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
falcon-mamba-7b-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
falcon-mamba-7b-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
falcon-mamba-7b-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
falcon-mamba-7b-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
falcon-mamba-7b-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
falcon-mamba-7b-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
falcon-mamba-7b-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
falcon-mamba-7b-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
falcon-mamba-7b-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
falcon-mamba-7b-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
falcon-mamba-7b-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- tiiuae/falcon-refinedweb
|
4 |
+
- HuggingFaceFW/fineweb-edu
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
license: other
|
8 |
+
license_name: falcon-mamba-7b-license
|
9 |
+
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
|
10 |
+
base_model: tiiuae/falcon-mamba-7b-instruct
|
11 |
+
pipeline_tag: text-generation
|
12 |
+
inference: true
|
13 |
+
tags:
|
14 |
+
- TensorBlock
|
15 |
+
- GGUF
|
16 |
+
---
|
17 |
+
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
+
</div>
|
21 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
22 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
24 |
+
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>
|
25 |
+
</p>
|
26 |
+
</div>
|
27 |
+
</div>
|
28 |
+
|
29 |
+
## tiiuae/falcon-mamba-7b-instruct - GGUF
|
30 |
+
|
31 |
+
This repo contains GGUF format model files for [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct).
|
32 |
+
|
33 |
+
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).
|
34 |
+
|
35 |
+
<div style="text-align: left; margin: 20px 0;">
|
36 |
+
<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;">
|
37 |
+
Run them on the TensorBlock client using your local machine ↗
|
38 |
+
</a>
|
39 |
+
</div>
|
40 |
+
|
41 |
+
## Prompt template
|
42 |
+
|
43 |
+
```
|
44 |
+
<|begin_of_text|><|im_start|>system
|
45 |
+
{system_prompt}<|im_end|>
|
46 |
+
<|im_start|>user
|
47 |
+
{prompt}<|im_end|>
|
48 |
+
<|im_start|>assistant
|
49 |
+
```
|
50 |
+
|
51 |
+
## Model file specification
|
52 |
+
|
53 |
+
| Filename | Quant type | File Size | Description |
|
54 |
+
| -------- | ---------- | --------- | ----------- |
|
55 |
+
| [falcon-mamba-7b-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q2_K.gguf) | Q2_K | 2.389 GB | smallest, significant quality loss - not recommended for most purposes |
|
56 |
+
| [falcon-mamba-7b-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q3_K_S.gguf) | Q3_K_S | 3.050 GB | very small, high quality loss |
|
57 |
+
| [falcon-mamba-7b-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q3_K_M.gguf) | Q3_K_M | 3.050 GB | very small, high quality loss |
|
58 |
+
| [falcon-mamba-7b-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q3_K_L.gguf) | Q3_K_L | 3.050 GB | small, substantial quality loss |
|
59 |
+
| [falcon-mamba-7b-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q4_0.gguf) | Q4_0 | 3.915 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
60 |
+
| [falcon-mamba-7b-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q4_K_S.gguf) | Q4_K_S | 3.915 GB | small, greater quality loss |
|
61 |
+
| [falcon-mamba-7b-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q4_K_M.gguf) | Q4_K_M | 3.915 GB | medium, balanced quality - recommended |
|
62 |
+
| [falcon-mamba-7b-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q5_0.gguf) | Q5_0 | 4.730 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
63 |
+
| [falcon-mamba-7b-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q5_K_S.gguf) | Q5_K_S | 4.730 GB | large, low quality loss - recommended |
|
64 |
+
| [falcon-mamba-7b-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q5_K_M.gguf) | Q5_K_M | 4.730 GB | large, very low quality loss - recommended |
|
65 |
+
| [falcon-mamba-7b-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q6_K.gguf) | Q6_K | 5.595 GB | very large, extremely low quality loss |
|
66 |
+
| [falcon-mamba-7b-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-instruct-GGUF/blob/main/falcon-mamba-7b-instruct-Q8_0.gguf) | Q8_0 | 7.232 GB | very large, extremely low quality loss - not recommended |
|
67 |
+
|
68 |
+
|
69 |
+
## Downloading instruction
|
70 |
+
|
71 |
+
### Command line
|
72 |
+
|
73 |
+
Firstly, install Huggingface Client
|
74 |
+
|
75 |
+
```shell
|
76 |
+
pip install -U "huggingface_hub[cli]"
|
77 |
+
```
|
78 |
+
|
79 |
+
Then, downoad the individual model file the a local directory
|
80 |
+
|
81 |
+
```shell
|
82 |
+
huggingface-cli download tensorblock/falcon-mamba-7b-instruct-GGUF --include "falcon-mamba-7b-instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
83 |
+
```
|
84 |
+
|
85 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
86 |
+
|
87 |
+
```shell
|
88 |
+
huggingface-cli download tensorblock/falcon-mamba-7b-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
89 |
+
```
|
falcon-mamba-7b-instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afe9a87f4f06acb6ba105854a0d84844d960ddbd92110cf6cad02fe1b6d4d372
|
3 |
+
size 2565011904
|
falcon-mamba-7b-instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bc74489cbb24ee073a39ce23ca53dec07265bb42a51cd940939a6b9db723282
|
3 |
+
size 3275340224
|
falcon-mamba-7b-instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b74d3d74dae190e7a3e1b5ee33377fd9007e2411ef057249efeccd01f965fd1
|
3 |
+
size 3275340224
|
falcon-mamba-7b-instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bbe9752d734244bb4f59a608a2cd1762e2db32fa2d8dd7fc986ed3fc83fcb6b
|
3 |
+
size 3275340224
|
falcon-mamba-7b-instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6224d9ecf313cd954fb58d69e69256c144f58931d2f11355363addecaa30d1e6
|
3 |
+
size 4204231104
|
falcon-mamba-7b-instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c8f873ca3257296140bf3cd5657a903b77565870bdf67ac62a2671e8461b3fd
|
3 |
+
size 4204231104
|
falcon-mamba-7b-instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:078054bb2dc331262195279e255db51149c74716b63bf41b1b51acfc125cf992
|
3 |
+
size 4204231104
|
falcon-mamba-7b-instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4354cba256aefc18f25aff425df1f4398503f452329765a362d0fe0d1e4aa4b1
|
3 |
+
size 5078481344
|
falcon-mamba-7b-instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52b043f630f194771b414f11a4edf9da49d2fcf6e93434e20026fb47df873e09
|
3 |
+
size 5078481344
|
falcon-mamba-7b-instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39378e8adf0b30cebcecfcce376f4848de9974e16bc7c19a18aaa14907936f8e
|
3 |
+
size 5078481344
|
falcon-mamba-7b-instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1ad0ad8112ebf6aa3c54727ab7a5acde95720c89c0617a2abd8f418431a91e9
|
3 |
+
size 6007372224
|
falcon-mamba-7b-instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:151002e65b3d4ab1110d641c48091fb031d6bf4b31248fb92e10db644e70f707
|
3 |
+
size 7765735872
|