Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +112 -0
- aya-expanse-32b-Q2_K.gguf +3 -0
- aya-expanse-32b-Q3_K_L.gguf +3 -0
- aya-expanse-32b-Q3_K_M.gguf +3 -0
- aya-expanse-32b-Q3_K_S.gguf +3 -0
- aya-expanse-32b-Q4_0.gguf +3 -0
- aya-expanse-32b-Q4_K_M.gguf +3 -0
- aya-expanse-32b-Q4_K_S.gguf +3 -0
- aya-expanse-32b-Q5_0.gguf +3 -0
- aya-expanse-32b-Q5_K_M.gguf +3 -0
- aya-expanse-32b-Q5_K_S.gguf +3 -0
- aya-expanse-32b-Q6_K.gguf +3 -0
- aya-expanse-32b-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 |
+
aya-expanse-32b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
aya-expanse-32b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
aya-expanse-32b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
aya-expanse-32b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
aya-expanse-32b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
aya-expanse-32b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
aya-expanse-32b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
aya-expanse-32b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
aya-expanse-32b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
aya-expanse-32b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
aya-expanse-32b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
aya-expanse-32b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
inference: false
|
| 3 |
+
library_name: transformers
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
- fr
|
| 7 |
+
- de
|
| 8 |
+
- es
|
| 9 |
+
- it
|
| 10 |
+
- pt
|
| 11 |
+
- ja
|
| 12 |
+
- ko
|
| 13 |
+
- zh
|
| 14 |
+
- ar
|
| 15 |
+
- el
|
| 16 |
+
- fa
|
| 17 |
+
- pl
|
| 18 |
+
- id
|
| 19 |
+
- cs
|
| 20 |
+
- he
|
| 21 |
+
- hi
|
| 22 |
+
- nl
|
| 23 |
+
- ro
|
| 24 |
+
- ru
|
| 25 |
+
- tr
|
| 26 |
+
- uk
|
| 27 |
+
- vi
|
| 28 |
+
license: cc-by-nc-4.0
|
| 29 |
+
extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
|
| 30 |
+
acknowledge that the information you provide will be collected, used, and shared
|
| 31 |
+
in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
|
| 32 |
+
receive email updates about C4AI and Cohere research, events, products and services.
|
| 33 |
+
You can unsubscribe at any time.
|
| 34 |
+
extra_gated_fields:
|
| 35 |
+
Name: text
|
| 36 |
+
Affiliation: text
|
| 37 |
+
Country: country
|
| 38 |
+
I agree to use this model for non-commercial use ONLY: checkbox
|
| 39 |
+
tags:
|
| 40 |
+
- TensorBlock
|
| 41 |
+
- GGUF
|
| 42 |
+
base_model: CohereForAI/aya-expanse-32b
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 46 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 47 |
+
</div>
|
| 48 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
| 49 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
| 50 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
| 51 |
+
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>
|
| 52 |
+
</p>
|
| 53 |
+
</div>
|
| 54 |
+
</div>
|
| 55 |
+
|
| 56 |
+
## CohereForAI/aya-expanse-32b - GGUF
|
| 57 |
+
|
| 58 |
+
This repo contains GGUF format model files for [CohereForAI/aya-expanse-32b](https://huggingface.co/CohereForAI/aya-expanse-32b).
|
| 59 |
+
|
| 60 |
+
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).
|
| 61 |
+
|
| 62 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 63 |
+
<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;">
|
| 64 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 65 |
+
</a>
|
| 66 |
+
</div>
|
| 67 |
+
|
| 68 |
+
## Prompt template
|
| 69 |
+
|
| 70 |
+
```
|
| 71 |
+
<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
|
| 72 |
+
```
|
| 73 |
+
|
| 74 |
+
## Model file specification
|
| 75 |
+
|
| 76 |
+
| Filename | Quant type | File Size | Description |
|
| 77 |
+
| -------- | ---------- | --------- | ----------- |
|
| 78 |
+
| [aya-expanse-32b-Q2_K.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q2_K.gguf) | Q2_K | 12.811 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 79 |
+
| [aya-expanse-32b-Q3_K_S.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q3_K_S.gguf) | Q3_K_S | 14.709 GB | very small, high quality loss |
|
| 80 |
+
| [aya-expanse-32b-Q3_K_M.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q3_K_M.gguf) | Q3_K_M | 16.232 GB | very small, high quality loss |
|
| 81 |
+
| [aya-expanse-32b-Q3_K_L.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q3_K_L.gguf) | Q3_K_L | 17.563 GB | small, substantial quality loss |
|
| 82 |
+
| [aya-expanse-32b-Q4_0.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q4_0.gguf) | Q4_0 | 18.719 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 83 |
+
| [aya-expanse-32b-Q4_K_S.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q4_K_S.gguf) | Q4_K_S | 18.850 GB | small, greater quality loss |
|
| 84 |
+
| [aya-expanse-32b-Q4_K_M.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q4_K_M.gguf) | Q4_K_M | 19.801 GB | medium, balanced quality - recommended |
|
| 85 |
+
| [aya-expanse-32b-Q5_0.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q5_0.gguf) | Q5_0 | 22.494 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 86 |
+
| [aya-expanse-32b-Q5_K_S.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q5_K_S.gguf) | Q5_K_S | 22.494 GB | large, low quality loss - recommended |
|
| 87 |
+
| [aya-expanse-32b-Q5_K_M.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q5_K_M.gguf) | Q5_K_M | 23.051 GB | large, very low quality loss - recommended |
|
| 88 |
+
| [aya-expanse-32b-Q6_K.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q6_K.gguf) | Q6_K | 26.505 GB | very large, extremely low quality loss |
|
| 89 |
+
| [aya-expanse-32b-Q8_0.gguf](https://huggingface.co/tensorblock/aya-expanse-32b-GGUF/blob/main/aya-expanse-32b-Q8_0.gguf) | Q8_0 | 34.327 GB | very large, extremely low quality loss - not recommended |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
## Downloading instruction
|
| 93 |
+
|
| 94 |
+
### Command line
|
| 95 |
+
|
| 96 |
+
Firstly, install Huggingface Client
|
| 97 |
+
|
| 98 |
+
```shell
|
| 99 |
+
pip install -U "huggingface_hub[cli]"
|
| 100 |
+
```
|
| 101 |
+
|
| 102 |
+
Then, downoad the individual model file the a local directory
|
| 103 |
+
|
| 104 |
+
```shell
|
| 105 |
+
huggingface-cli download tensorblock/aya-expanse-32b-GGUF --include "aya-expanse-32b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
| 106 |
+
```
|
| 107 |
+
|
| 108 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
| 109 |
+
|
| 110 |
+
```shell
|
| 111 |
+
huggingface-cli download tensorblock/aya-expanse-32b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
| 112 |
+
```
|
aya-expanse-32b-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27f1bb8962600b722af50366f425bd21df352e145fb2e6d1dd78aefd43f75032
|
| 3 |
+
size 12810755712
|
aya-expanse-32b-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64bf904052206de3ee334be8a9eb3892a9a4203606f0d0b315827d11214379ee
|
| 3 |
+
size 17563426432
|
aya-expanse-32b-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85187a60498184cd66917f05177e5190139312474be0d9fe0b7b246a577af376
|
| 3 |
+
size 16231734912
|
aya-expanse-32b-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df117bc67567e6d133604dcee12865a496908c6e553132aaaebf22af38b51b5f
|
| 3 |
+
size 14708678272
|
aya-expanse-32b-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a8f0fa0962cc0d0b53bcc10449a3744a4fb4126105562e811ec0e76e5be74cf
|
| 3 |
+
size 18719481472
|
aya-expanse-32b-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a813093c30557c09b56e54dcd700506fa49140f689c08a25809d9f00e59bbe1e
|
| 3 |
+
size 19800825472
|
aya-expanse-32b-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88fe1b72d887a9d58a5e5d15a2ab5d669cbd715b3ff3a6ff90df2352d8110417
|
| 3 |
+
size 18849504896
|
aya-expanse-32b-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2106f3b66f661dba0a8b3f9f9d02aa4cbb36f74cd2ea920eb1bd6f202fe67020
|
| 3 |
+
size 22494355072
|
aya-expanse-32b-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee00f90c5b15b22e4058b258b945c0e35c8d9e2876d40137770f0dc6dd447feb
|
| 3 |
+
size 23051411072
|
aya-expanse-32b-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd2045b26cd4fe588ab828318dd2deb447ea9adbe66ac1ed489d3efee40da33
|
| 3 |
+
size 22494355072
|
aya-expanse-32b-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bf166ce2811d6d68d7d58279a06dcd39e66f2838a44332352e11d21f70df6ae
|
| 3 |
+
size 26505158272
|
aya-expanse-32b-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:807c366d804beae01d3d2954945c91b27befb671bcf40ba6682eb73739592f91
|
| 3 |
+
size 34326879872
|