bartowski/Zenith_4B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/Zenith_4B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-21 04:37:12 +08:00
commit 8b52bb7d55
25 changed files with 248 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
.gitattributes vendored Normal file
View File

@@ -0,0 +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
*.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
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Zenith_4B.imatrix filter=lfs diff=lfs merge=lfs -text

124
README.md Normal file
View File

@@ -0,0 +1,124 @@
---
base_model: FourOhFour/Zenith_4B
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Zenith_4B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3658">b3658</a> for quantization.
Original model: https://huggingface.co/FourOhFour/Zenith_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
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Zenith_4B-f16.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-f16.gguf) | f16 | 9.03GB | false | Full F16 weights. |
| [Zenith_4B-Q8_0.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q8_0.gguf) | Q8_0 | 4.80GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Zenith_4B-Q6_K_L.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_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*. |
| [Zenith_4B-Q6_K.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q6_K.gguf) | Q6_K | 3.71GB | false | Very high quality, near perfect, *recommended*. |
| [Zenith_4B-Q5_K_L.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q5_K_L.gguf) | Q5_K_L | 3.47GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Zenith_4B-Q5_K_M.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q5_K_M.gguf) | Q5_K_M | 3.23GB | false | High quality, *recommended*. |
| [Zenith_4B-Q5_K_S.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q5_K_S.gguf) | Q5_K_S | 3.16GB | false | High quality, *recommended*. |
| [Zenith_4B-Q4_K_L.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_K_L.gguf) | Q4_K_L | 3.07GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Zenith_4B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q3_K_XL.gguf) | Q3_K_XL | 2.81GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Zenith_4B-Q4_K_M.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_K_M.gguf) | Q4_K_M | 2.78GB | false | Good quality, default size for must use cases, *recommended*. |
| [Zenith_4B-Q4_K_S.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_K_S.gguf) | Q4_K_S | 2.66GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Zenith_4B-Q4_0.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_0.gguf) | Q4_0 | 2.66GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Zenith_4B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_0_8_8.gguf) | Q4_0_8_8 | 2.65GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [Zenith_4B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_0_4_8.gguf) | Q4_0_4_8 | 2.65GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [Zenith_4B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q4_0_4_4.gguf) | Q4_0_4_4 | 2.65GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [Zenith_4B-IQ4_XS.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-IQ4_XS.gguf) | IQ4_XS | 2.54GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Zenith_4B-Q3_K_L.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q3_K_L.gguf) | Q3_K_L | 2.46GB | false | Lower quality but usable, good for low RAM availability. |
| [Zenith_4B-Q3_K_M.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q3_K_M.gguf) | Q3_K_M | 2.30GB | false | Low quality. |
| [Zenith_4B-IQ3_M.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-IQ3_M.gguf) | IQ3_M | 2.18GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Zenith_4B-Q3_K_S.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-Q3_K_S.gguf) | Q3_K_S | 2.10GB | false | Low quality, not recommended. |
| [Zenith_4B-IQ3_XS.gguf](https://huggingface.co/bartowski/Zenith_4B-GGUF/blob/main/Zenith_4B-IQ3_XS.gguf) | IQ3_XS | 2.03GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
## Q4_0_X_X
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!).
## 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!
## 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
## 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/Zenith_4B-GGUF --include "Zenith_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/Zenith_4B-GGUF --include "Zenith_4B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Zenith_4B-Q8_0) or download them all in place (./)
## 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.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

3
Zenith_4B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb3507db14b278717cff1751702223644b6526b7cb6e5a2da77ee0e6bb41b58e
size 2183414912

3
Zenith_4B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69871db5957d552413e139cab11a91ba7fbf671ee8deb1aa54c110cfae458777
size 2027603072

3
Zenith_4B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:70be87c85e25642091f8a2f15f229f87c0e1e385634cd0993d4cdd1a77d20745
size 2535545984

3
Zenith_4B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7efe8f03f31e21add02b61c1cb1af97a9096b5232e8fcd0728880fb733644489
size 2464859264

3
Zenith_4B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b00e8be5b47d1688e691c1a5596467b98dd919ea62c8c65863e1122058a0c02f
size 2296562816

3
Zenith_4B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c5bc38fd0c5fc25fb31d87183e71aad0dc233deba7456cea343bd3321102e648
size 2101527680

3
Zenith_4B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3e03d3f34978fe2837e06a4b4a21af6e07049eea86cea334e955abc656bb226
size 2809611392

3
Zenith_4B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:072ad4ce512803813fd4c60f8a891f66ae059568b7b5f3e50f97f8a5a8c48c41
size 2655599744

3
Zenith_4B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5c40d83fc9928d93e74fe915c33858553e9504a99581e1400d9e59888f26572
size 2648521856

3
Zenith_4B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4391cf21c1d0a45ba3c01330c343c9c74da07634fff9f28bb1cfe0e63d12e043
size 2648521856

3
Zenith_4B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e39a1ce65e708152d9fc715776a91aecb5f63dcb5f74d49c9986e4cb40f9a2b3
size 2648521856

3
Zenith_4B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12b3be1c291cf8779c716cca3f91b858de2cd399693bbf35625f22be61ad8676
size 3070706816

3
Zenith_4B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fcd76de9bb3558c6e9f9adf85d3b6f7e306cb6a4f7bd31dffaa8edfa90354c4
size 2778283136

3
Zenith_4B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0bda5b0ce988e22a819c0cee50b480f1cbf1a40d39c77a7aa73c65588f9c42b0
size 2664250496

3
Zenith_4B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37f2095b3aa8e43f5893eddeb02e70bb247318fec9cb46dd65f45e0afcea7340
size 3473360000

3
Zenith_4B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8ce717490a930df96ca2b38d7752eb316024bf0a56beffeb5b196937ae6915e
size 3230186624

3
Zenith_4B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dee458a56886f960b48de171f9eee3357f87cedbc41ce82a54e987d3686eb931
size 3163339904

3
Zenith_4B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6b049484a6d189bd9f2a84d9359a46ba875521b446e5304aeeedb245ea896bb
size 3710334080

3
Zenith_4B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e5301e01326d043c47a17eda04973b817c4eea4d6a9ab974654a6446530bab78
size 3901179008

3
Zenith_4B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b85fb5879144b6b906a95a8a5b711dc063aecd8a1b3e14ac28349e522d3c0698
size 4803216512

3
Zenith_4B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a18a9c3bda13522c99d676c99200e4c4029ca52e115e2831cd07fcb208c9e23
size 9033728896

3
Zenith_4B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5ed21488ef3ba0f958dac1ea5b3879eb03928a96364b7fc139f6fa8f6804bdc
size 3677450

1
configuration.json Normal file
View File

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