bartowski/NuExtract-v1.5-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/NuExtract-v1.5-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 12:31:07 +08:00
commit 01f176909d
28 changed files with 261 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +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
*.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
NuExtract-v1.5-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5-f16.gguf filter=lfs diff=lfs merge=lfs -text
NuExtract-v1.5.imatrix filter=lfs diff=lfs merge=lfs -text

3
NuExtract-v1.5-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20beeafe141f35ae18304a814a5944f014902a5bda6dd670c09bc3fe673cd505
size 1316395424

3
NuExtract-v1.5-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1a824eedfdc6bae41a966d56557b8262f95d25b0e5dde79c81433247b7733a3
size 1855600544

3
NuExtract-v1.5-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a6ea32b0eb104e95156f9c68d9024ee57ae9914c5e8bf2ced558f5ae441ca2bf
size 1625175968

3
NuExtract-v1.5-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f800b284395e2e312b0b4ef555f01a345048d6771ac069f2d888477b4684a040
size 2059853216

3
NuExtract-v1.5-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:70fd2375343bcac4871b551ab1529579447788a6fb3c9084cfd8982585e0d54e
size 1416204704

3
NuExtract-v1.5-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e149224040de6741af434941f641143baad5b802c37efead85293d66ae4073e
size 1512396704

3
NuExtract-v1.5-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d9bdff8e5ac56afcc47fd555117925220ca299090fb077661bc845ed18f2154f
size 2087597984

3
NuExtract-v1.5-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c826b8211667dbfbef7ee1ccc2ce1e6c5470da457ef014e9072afa544f16356
size 1955477408

3
NuExtract-v1.5-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f59f923eac8a3314ff8893d21e956f58e02f37a8da69186903def4f556b11971
size 1681799072

3
NuExtract-v1.5-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21fbb1bfabd5232dfb410108e18fe645593866505ff914db168af1c0af5195be
size 2173786016

3
NuExtract-v1.5-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4eb6bad05a4116d540f8a3e2ba4ddbe6ec2460aaef1244f5e4e6255f16534a59
size 2182469024

3
NuExtract-v1.5-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:829cc8c0def5dc3d8a3386b4f5e6b23eb76425bf5d1388214fedf4794d9751e4
size 2176177568

3
NuExtract-v1.5-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3b43804f5786e68a627891f6ca8db6860e54420e106a6238a034800799ab782
size 2176177568

3
NuExtract-v1.5-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f8fda54cf07d76d3954176d18cc2665d6250a53a88de71230ae044d6c7ecc2f
size 2176177568

3
NuExtract-v1.5-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4cb2c70b4965a4d33b8f74280463e7003d28e5ad789e47c50cb089d67d7805d4
size 2466338720

3
NuExtract-v1.5-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0db8d385745db71a5760feefa81dc1e99b38e3d243d0a5cced12a499e0ec6457
size 2393232800

3
NuExtract-v1.5-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38945b174bd28c8b1bd2a314dcee5a2670ac1cc755ba073383b39edca5386fe0
size 2188760480

3
NuExtract-v1.5-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c25ecb985f5bb2c9b4b8ff3cd269cf651a3f40535f17e4e2f577168eda0067d
size 2876069792

3
NuExtract-v1.5-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8bcc939909ae6d2181557b8e79afbfb11526442f0556bd22bd337cd1a50b2889
size 2815276448

3
NuExtract-v1.5-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c1fdc9a55c88c5de948cfd116a3d9b478e38bc1151d6c67e37013819f21f8ca
size 2641474976

3
NuExtract-v1.5-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7104e6349a0d3c6e39c9379150fd7ebdecc1b4b9e0865a3eec19f538b2b74c49
size 3135853472

3
NuExtract-v1.5-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:06853ff9c7e18c7f7be4c59edda8c0b84b80678f9492cc42848669ccd8d22ddf
size 3183564704

3
NuExtract-v1.5-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9165a5218aff1dcf9b48c49b9555379ed7ec901d55543c80e9cafac0af40d047
size 4061222816

3
NuExtract-v1.5-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15d67352578b3cefabad13a07d6b0775379375db8e01288dda34945cc1ee2857
size 7643297440

3
NuExtract-v1.5.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab6a3e6d71c3aa3bfac10c089f9a48945a4117330715e3355cb410e6f5308852
size 2232616

125
README.md Normal file
View File

@@ -0,0 +1,125 @@
---
base_model: numind/NuExtract-v1.5
language:
- multilingual
license: mit
pipeline_tag: text-generation
tags:
- nlp
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of NuExtract-v1.5
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3901">b3901</a> for quantization.
Original model: https://huggingface.co/numind/NuExtract-v1.5
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
```
<|system|> {system_prompt}<|end|><|user|> {prompt}<|end|><|assistant|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [NuExtract-v1.5-f16.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-f16.gguf) | f16 | 7.64GB | false | Full F16 weights. |
| [NuExtract-v1.5-Q8_0.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q8_0.gguf) | Q8_0 | 4.06GB | false | Extremely high quality, generally unneeded but max available quant. |
| [NuExtract-v1.5-Q6_K_L.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q6_K_L.gguf) | Q6_K_L | 3.18GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [NuExtract-v1.5-Q6_K.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q6_K.gguf) | Q6_K | 3.14GB | false | Very high quality, near perfect, *recommended*. |
| [NuExtract-v1.5-Q5_K_L.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q5_K_L.gguf) | Q5_K_L | 2.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [NuExtract-v1.5-Q5_K_M.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q5_K_M.gguf) | Q5_K_M | 2.82GB | false | High quality, *recommended*. |
| [NuExtract-v1.5-Q5_K_S.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q5_K_S.gguf) | Q5_K_S | 2.64GB | false | High quality, *recommended*. |
| [NuExtract-v1.5-Q4_K_L.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_K_L.gguf) | Q4_K_L | 2.47GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [NuExtract-v1.5-Q4_K_M.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_K_M.gguf) | Q4_K_M | 2.39GB | false | Good quality, default size for must use cases, *recommended*. |
| [NuExtract-v1.5-Q4_K_S.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_K_S.gguf) | Q4_K_S | 2.19GB | false | Slightly lower quality with more space savings, *recommended*. |
| [NuExtract-v1.5-Q4_0_8_8.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_0_8_8.gguf) | Q4_0_8_8 | 2.18GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [NuExtract-v1.5-Q4_0_4_8.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_0_4_8.gguf) | Q4_0_4_8 | 2.18GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [NuExtract-v1.5-Q4_0_4_4.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_0_4_4.gguf) | Q4_0_4_4 | 2.18GB | 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*. |
| [NuExtract-v1.5-Q4_0.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q4_0.gguf) | Q4_0 | 2.18GB | false | Legacy format, generally not worth using over similarly sized formats |
| [NuExtract-v1.5-Q3_K_XL.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q3_K_XL.gguf) | Q3_K_XL | 2.17GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [NuExtract-v1.5-Q3_K_L.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q3_K_L.gguf) | Q3_K_L | 2.09GB | false | Lower quality but usable, good for low RAM availability. |
| [NuExtract-v1.5-IQ4_XS.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-IQ4_XS.gguf) | IQ4_XS | 2.06GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [NuExtract-v1.5-Q3_K_M.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q3_K_M.gguf) | Q3_K_M | 1.96GB | false | Low quality. |
| [NuExtract-v1.5-IQ3_M.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-IQ3_M.gguf) | IQ3_M | 1.86GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [NuExtract-v1.5-Q3_K_S.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q3_K_S.gguf) | Q3_K_S | 1.68GB | false | Low quality, not recommended. |
| [NuExtract-v1.5-IQ3_XS.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-IQ3_XS.gguf) | IQ3_XS | 1.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [NuExtract-v1.5-Q2_K_L.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q2_K_L.gguf) | Q2_K_L | 1.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [NuExtract-v1.5-Q2_K.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-Q2_K.gguf) | Q2_K | 1.42GB | false | Very low quality but surprisingly usable. |
| [NuExtract-v1.5-IQ2_M.gguf](https://huggingface.co/bartowski/NuExtract-v1.5-GGUF/blob/main/NuExtract-v1.5-IQ2_M.gguf) | IQ2_M | 1.32GB | 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/NuExtract-v1.5-GGUF --include "NuExtract-v1.5-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/NuExtract-v1.5-GGUF --include "NuExtract-v1.5-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (NuExtract-v1.5-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}