bartowski/aya-expanse-8b-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update metadata with huggingface_hub

Browse Source
This commit is contained in:
ai-modelscope
2024-11-24 18:58:09 +08:00
parent 3618343615
commit 276a7baa0c
28 changed files with 262 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
.gitattributes vendored
View File

@@ -1,38 +1,60 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b-f16.gguf filter=lfs diff=lfs merge=lfs -text
aya-expanse-8b.imatrix filter=lfs diff=lfs merge=lfs -text

191
README.md
View File

@@ -1,47 +1,156 @@
---
license: Apache License 2.0
#model-type:
##如 gpt、phi、llama、chatglm、baichuan 等
#- gpt
#domain:
##如 nlp、cv、audio、multi-modal
#- nlp
#language:
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
#- cn
#metrics:
##如 CIDEr、Blue、ROUGE 等
#- CIDEr
#tags:
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
#- pretrained
#tools:
##如 vllm、fastchat、llamacpp、AdaSeq 等
#- vllm
base_model: CohereForAI/aya-expanse-8b
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
pipeline_tag: text-generation
quantized_by: bartowski
inference: false
extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
acknowledge that the information you provide will be collected, used, and shared
in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
receive email updates about C4AI and Cohere research, events, products and services.
You can unsubscribe at any time.
extra_gated_fields:
Name: text
Affiliation: text
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
---
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
SDK下载
```bash
#安装ModelScope
pip install modelscope
## Llamacpp imatrix Quantizations of aya-expanse-8b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3930">b3930</a> for quantization.
Original model: https://huggingface.co/CohereForAI/aya-expanse-8b
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('bartowski/aya-expanse-8b-GGUF')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/bartowski/aya-expanse-8b-GGUF.git
<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|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
```
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [aya-expanse-8b-f16.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [aya-expanse-8b-Q8_0.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [aya-expanse-8b-Q6_K_L.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [aya-expanse-8b-Q6_K.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [aya-expanse-8b-Q5_K_L.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [aya-expanse-8b-Q5_K_M.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q5_K_M.gguf) | Q5_K_M | 5.80GB | false | High quality, *recommended*. |
| [aya-expanse-8b-Q5_K_S.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q5_K_S.gguf) | Q5_K_S | 5.67GB | false | High quality, *recommended*. |
| [aya-expanse-8b-Q4_K_L.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [aya-expanse-8b-Q4_K_M.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_K_M.gguf) | Q4_K_M | 5.06GB | false | Good quality, default size for must use cases, *recommended*. |
| [aya-expanse-8b-Q4_K_S.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_K_S.gguf) | Q4_K_S | 4.83GB | false | Slightly lower quality with more space savings, *recommended*. |
| [aya-expanse-8b-Q4_0.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_0.gguf) | Q4_0 | 4.81GB | false | Legacy format, generally not worth using over similarly sized formats |
| [aya-expanse-8b-Q4_0_8_8.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.80GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [aya-expanse-8b-Q4_0_4_8.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.80GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [aya-expanse-8b-Q4_0_4_4.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.80GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. *Don't use on Mac or Windows*. |
| [aya-expanse-8b-Q3_K_XL.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [aya-expanse-8b-IQ4_XS.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-IQ4_XS.gguf) | IQ4_XS | 4.60GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [aya-expanse-8b-Q3_K_L.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q3_K_L.gguf) | Q3_K_L | 4.53GB | false | Lower quality but usable, good for low RAM availability. |
| [aya-expanse-8b-Q3_K_M.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q3_K_M.gguf) | Q3_K_M | 4.22GB | false | Low quality. |
| [aya-expanse-8b-IQ3_M.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-IQ3_M.gguf) | IQ3_M | 3.99GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [aya-expanse-8b-Q3_K_S.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q3_K_S.gguf) | Q3_K_S | 3.87GB | false | Low quality, not recommended. |
| [aya-expanse-8b-IQ3_XS.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-IQ3_XS.gguf) | IQ3_XS | 3.72GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [aya-expanse-8b-Q2_K_L.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [aya-expanse-8b-Q2_K.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-Q2_K.gguf) | Q2_K | 3.44GB | false | Very low quality but surprisingly usable. |
| [aya-expanse-8b-IQ2_M.gguf](https://huggingface.co/bartowski/aya-expanse-8b-GGUF/blob/main/aya-expanse-8b-IQ2_M.gguf) | IQ2_M | 3.08GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/aya-expanse-8b-GGUF --include "aya-expanse-8b-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/aya-expanse-8b-GGUF --include "aya-expanse-8b-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (aya-expanse-8b-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
Thank you ZeroWw for the inspiration to experiment with embed/output
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

3
aya-expanse-8b-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:facbf3b6d04a40257a89660c5e99ee1d48fa721b1b3854cf061858c91adef792
size 3084807872

3
aya-expanse-8b-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff12433fa5f1674c0ae61580a56fd090be7008b5ebcd8de2b4588ba1dbca0daf
size 3990843072

3
aya-expanse-8b-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5866f97fca03f84a1f6f0285dbf4b10753473f424a0c3ff477e3246c27756edc
size 3724766912

3
aya-expanse-8b-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a356b02a1106152c26ecf2a550390ab602f2a165b6e1240298ba6bf808c2697
size 4600327872

3
aya-expanse-8b-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e0067b2ba818490c377e606fbefc223c93c42f832af204bb1ec0870c592d669c
size 3438505664

3
aya-expanse-8b-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90ad8cce0ba1d93d2fc76ccaf716d9ec15c864bc2b90bbb93414d5016f4115f4
size 3692457664

3
aya-expanse-8b-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14a4c9210a73e4c9d27dc0f6889b349a86adc033bc6c833bc7e06b5cd6092c84
size 4527976128

3
aya-expanse-8b-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5b61a2e1595d896e39c324cc206e46af8e37d21869f7dcb3bed00115c4be3183
size 4224937664

3
aya-expanse-8b-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7923337d0228c2a54217f9dd87c3001c34330916762cac9d673ad1c5c1986cb
size 3870518976

3
aya-expanse-8b-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3655b756aad22d8de4473ea8ae9dd9adce9d051cbe664d4972848a37dce5c051
size 4781928128

3
aya-expanse-8b-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8eebc678446e470615c38ea7adc17716bc194a1b103cd7d9cd01ebdeef93a790
size 4812140224

3
aya-expanse-8b-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02a4d762fe1f4d5c46e3af567f975eb43f02dc18fa6cb576fca7888534b618bb
size 4797460160

3
aya-expanse-8b-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e277da4b45919906ce55a8a02c22f381ce9374bdcc00ef58eaa9b7323653a149
size 4797460160

3
aya-expanse-8b-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85db75a9cf63d99426673c1f9dbb6e2138a6b1c19b45593adb36463f946df915
size 4797460160

3
aya-expanse-8b-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d03f9baef8964fb02c8b2d758cfb950d249baa655ee6ef9efcc4fb3d92c31ff2
size 5310934720

3
aya-expanse-8b-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9592bad943fe56cf93200286a0a4b00a158cd84a408f227b9978ec5879002fb8
size 5056982720

3
aya-expanse-8b-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:678f247d9fd58c3644995533a81c8ca34a89e8730834394ba45cc3ff3c9ba85f
size 4828917440

3
aya-expanse-8b-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f93e852e41b746f06d0e983eb8b9dab8c3e7474ae627717794690c175c93ad9
size 6057520832

3
aya-expanse-8b-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e38abb7db6bbacaab6813774be2db5ccd14ff6a13a940f7ee311356b653bc60
size 5803568832

3
aya-expanse-8b-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:31165b8ca72076b990e26973f27154993af507ef84fe0021791c4c3050941ba8
size 5669875392

3
aya-expanse-8b-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d9ed3590a8b9cfbe41be1adc5fdf2270ab01be2cbd775d09c60155a9f3f75b6b
size 6596816576

3
aya-expanse-8b-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47bf5466e0e54be7836daffa23deacd77ba030b05e7be75147c93a7709e6401d
size 6850768576

3
aya-expanse-8b-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75e5bfef4bee065bf07903ad941cac35a2809ecd84baba098f5307645655c22d
size 8541073088

3
aya-expanse-8b-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a99b28badc2d3813f82131e2ebc70ee4afad017b58c0920e4de4a63777d34ab3
size 16067227072

3
aya-expanse-8b.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40f17fcab4c7bf1faace63cfffb8bfcbcf49d10d21c5f9c4dad747b64774912c
size 4988170

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}