bartowski/DigitalSoul-4B-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
2024-12-11 02:52:41 +08:00
parent 90968f0eef
commit e81c62642c
25 changed files with 218 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
.gitattributes vendored
View File

@@ -1,47 +1,57 @@
*.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
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B-f16.gguf filter=lfs diff=lfs merge=lfs -text
DigitalSoul-4B.imatrix filter=lfs diff=lfs merge=lfs -text

3
DigitalSoul-4B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5d6fc05b8650faa3daed375751c9b572d03efb14cd26f31cd310df67462d8b2
size 2235653472

3
DigitalSoul-4B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3654654c93e93ac32ff36fba067951bcc04b680fd29e0055e7b649410cceb81a
size 2578144608

3
DigitalSoul-4B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:649e3e62a49051896414fb31ef8296fee0e242750b4e70fba8dbda6fc5be50b6
size 1880382816

3
DigitalSoul-4B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:168ac2c2e622726febe0de3b954ab9d2f647e7ba6361187e1178d27ff6459e50
size 1975805280

3
DigitalSoul-4B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5858709b98fee1a0d02a7a4f89cba75d300d4309e4936c9914d880e5bedd2931
size 2557500768

3
DigitalSoul-4B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a7f3c7dd78f4171df56a50e0787d23aae18ab7245fafce09c41e11b338a0b26
size 2148752736

3
DigitalSoul-4B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cae2605e0397b823cfb990fdc1125029f0a6c535fee87c82517232723384b404
size 2652923232

3
DigitalSoul-4B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f5d1287fd8662031c754038b200b878817c0a8c6a75a57991ddc65f39ec617d
size 2718129504

3
DigitalSoul-4B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b39b930c04a67be0079106c29904257a06e74e9ceafcec42ff7f2abf24f768c
size 2710265184

3
DigitalSoul-4B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c2a093fb0ba2898ee6a5a5d9e6f61d9a378cbc57e1df5542afd7837dd8f69d8
size 2710265184

3
DigitalSoul-4B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:80eeb7269fb92568c7117731ceb657e3fe795a9790b0492d0fba871ad35d23ea
size 2710265184

3
DigitalSoul-4B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a4008ca3d8760d22fa7697792fba377434dce22ff39c582429c6a936b8ff761
size 2958968160

3
DigitalSoul-4B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a104e96f207fd74e992b03464ceea30d49f4c7ae78e9abefbf250d3519154fd
size 2863545696

3
DigitalSoul-4B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7dc9278878e76a197a337d066615c2018c823e611c47dcd202b1aed91f68543
size 2727566688

3
DigitalSoul-4B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:599338c97c7473b249ad651252b83efdc88f4ed7adfc7db0a6dcc114ab8dd873
size 3413132640

3
DigitalSoul-4B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ebf533dcbada74b2685de37df5c25a8e9d3edb266cfc0dd41fd52356d7ecdf3
size 3317710176

3
DigitalSoul-4B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0fae72388b433ba5f14f4099c0c94ed7fac324db3a08ca62fa56a469bbc61370
size 3238747488

3
DigitalSoul-4B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:126d588c9daa19d18c84d12dcb9574a3d8184a0ec424678f2e5f3c98efe0f11c
size 3800259936

3
DigitalSoul-4B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b53ac32e793a4d89b13b36eabb2cc8a46bc61dc08d33427a480d9b3fa513dafa
size 3895682400

3
DigitalSoul-4B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:439b3106566cb77940f6fb7341cdbd10ac810c752ef12a1452e084baae26b7e2
size 4919616864

3
DigitalSoul-4B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c38e29cc4cbf712953206da990d1a3bc6820a72f5ecefa7bbaed44e17f8bec31
size 9252611168

3
DigitalSoul-4B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4c0651a01423950c4f84c8aeacb10867bcba746625d646c3fd7dc03fa943583
size 4482596

160
README.md
View File

@@ -1,47 +1,125 @@
---
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: TroyDoesAI/DigitalSoul-4B
license: artistic-2.0
pipeline_tag: text-generation
quantized_by: bartowski
---
### 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 DigitalSoul-4B
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/TroyDoesAI/DigitalSoul-4B
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/DigitalSoul-4B-GGUF')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/bartowski/DigitalSoul-4B-GGUF.git
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 23 Oct 2024
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
<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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [DigitalSoul-4B-f16.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-f16.gguf) | f16 | 9.25GB | false | Full F16 weights. |
| [DigitalSoul-4B-Q8_0.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q8_0.gguf) | Q8_0 | 4.92GB | false | Extremely high quality, generally unneeded but max available quant. |
| [DigitalSoul-4B-Q6_K_L.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q6_K_L.gguf) | Q6_K_L | 3.90GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [DigitalSoul-4B-Q6_K.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q6_K.gguf) | Q6_K | 3.80GB | false | Very high quality, near perfect, *recommended*. |
| [DigitalSoul-4B-Q5_K_L.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q5_K_L.gguf) | Q5_K_L | 3.41GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [DigitalSoul-4B-Q5_K_M.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q5_K_M.gguf) | Q5_K_M | 3.32GB | false | High quality, *recommended*. |
| [DigitalSoul-4B-Q5_K_S.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q5_K_S.gguf) | Q5_K_S | 3.24GB | false | High quality, *recommended*. |
| [DigitalSoul-4B-Q4_K_L.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_K_L.gguf) | Q4_K_L | 2.96GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [DigitalSoul-4B-Q4_K_M.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_K_M.gguf) | Q4_K_M | 2.86GB | false | Good quality, default size for must use cases, *recommended*. |
| [DigitalSoul-4B-Q4_K_S.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_K_S.gguf) | Q4_K_S | 2.73GB | false | Slightly lower quality with more space savings, *recommended*. |
| [DigitalSoul-4B-Q4_0.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_0.gguf) | Q4_0 | 2.72GB | false | Legacy format, generally not worth using over similarly sized formats |
| [DigitalSoul-4B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_0_8_8.gguf) | Q4_0_8_8 | 2.71GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [DigitalSoul-4B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_0_4_8.gguf) | Q4_0_4_8 | 2.71GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [DigitalSoul-4B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q4_0_4_4.gguf) | Q4_0_4_4 | 2.71GB | 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*. |
| [DigitalSoul-4B-Q3_K_XL.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q3_K_XL.gguf) | Q3_K_XL | 2.65GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [DigitalSoul-4B-IQ4_XS.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-IQ4_XS.gguf) | IQ4_XS | 2.58GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [DigitalSoul-4B-Q3_K_L.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q3_K_L.gguf) | Q3_K_L | 2.56GB | false | Lower quality but usable, good for low RAM availability. |
| [DigitalSoul-4B-IQ3_M.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-IQ3_M.gguf) | IQ3_M | 2.24GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [DigitalSoul-4B-Q3_K_S.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q3_K_S.gguf) | Q3_K_S | 2.15GB | false | Low quality, not recommended. |
| [DigitalSoul-4B-Q2_K_L.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q2_K_L.gguf) | Q2_K_L | 1.98GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [DigitalSoul-4B-Q2_K.gguf](https://huggingface.co/bartowski/DigitalSoul-4B-GGUF/blob/main/DigitalSoul-4B-Q2_K.gguf) | Q2_K | 1.88GB | false | Very low quality but 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/DigitalSoul-4B-GGUF --include "DigitalSoul-4B-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/DigitalSoul-4B-GGUF --include "DigitalSoul-4B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (DigitalSoul-4B-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

1
configuration.json Normal file
View File

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