初始化项目,由ModelHub XC社区提供模型

Model: mradermacher/KAT-V1-40B-i1-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-20 16:26:20 +08:00
commit b59e4cfb52
26 changed files with 213 additions and 0 deletions

59
.gitattributes vendored Normal file
View File

@@ -0,0 +1,59 @@
*.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
imatrix.dat filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
KAT-V1-40B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text

3
KAT-V1-40B.i1-IQ1_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e20b67e593bad58080dbb9c0f420828f27d25768d7b47dd0217d30d1253d55a0
size 9716030816

3
KAT-V1-40B.i1-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e339f37e03e80a0e186c8f892caeade1c258262457e22c9d7878e39dc788a998
size 8893963616

3
KAT-V1-40B.i1-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2fef7c2eca8942140a142d65406b7139c27f1305166f218e1bc8c2fe2806677f
size 13861612896

3
KAT-V1-40B.i1-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:917d1c933dad29de58578e7e4e36a4bae2f6585f84659eb779f6160744903522
size 12765523296

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1647015f5650780bb259186b8151cc005332e1a97d08073d00de899e75957cc8
size 12247768416

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0fc263b6764a117d2b14798c0bd351c8cb53c01d36439e0febc4c9f451f168cf
size 11086142816

3
KAT-V1-40B.i1-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88424659e41b2acdc7c24ffca71603b5893816b5655637f576fc7d198733c503
size 18320293216

3
KAT-V1-40B.i1-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:653d869f4027c029d8ded623db8c8fe923afb9ea685d6d8cbd6c729500601460
size 17853758816

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e193c1d2781ee438185a79dad702ca4c26cb43d7992e6f5a4dc6f61118c06754
size 16939531616

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62e78c79f43b7c1321fec67b369cb2c3f09c8388990669f280ff669d9f471de0
size 15882579296

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c0108f9fdb4673df7092fff15eedc2794f20d4ab040d8e52ff95f648c7cafdbf
size 21851884896

3
KAT-V1-40B.i1-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ea3bdfa6a3c24d12861ae3fd3685b25025742eeab846e6a87ebf3318f344817
size 15218781536

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3cf9d012c92aa6303228395c02bc5c39976efb4cf74ccd44bbaf1cd5e5dff8f1
size 14187408736

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f83ee7b5af3fe5366c4f34b80a30c55b44c6acbba17b2a077d9fd40219254b2
size 21314059616

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:562432f9e03ecd68207fe951006e7fdc4c2bdb85013c7ceda7a7256e99592fb9
size 19724811616

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a038c771189d3e8541df83ba509395419896251a297093d56b731fae325d7f7
size 17853758816

3
KAT-V1-40B.i1-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1342af27c018a57eb7307782007905f380a4b9fb19fd3e841a656f0ae9b8477e
size 23118122336

3
KAT-V1-40B.i1-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d4fb81a6b48d785ce1461ea2b1504985f933853a45d7f0ebff00d2b464d6062c
size 25516248416

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a8d9cbd72b88b87080d5b8f9a8e2e551bdbf14cf0cc9f2d84d65c3cceb5b746
size 24569744736

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9eea12ea3db513bed1210b91437c97e8539a14e5cee59c8fa3690f9eb3eeb52
size 23259024736

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7690fb2502008528cdb4cda48f8c555941fad344ae3e6f9388be7c0ccf259e3a
size 28782726496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:180b8b3735802a86c1155bcecace41f20edb437e918673b23e5f07b1d7342623
size 28002848096

3
KAT-V1-40B.i1-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a67757d4b2e3dd7897fb7b276218ee4e6f08372bcb37f53ead33b4949851b9f2
size 33286872416

82
README.md Normal file
View File

@@ -0,0 +1,82 @@
---
base_model: Kwaipilot/KAT-V1-40B
language:
- multilingual
library_name: transformers
license: other
license_link: LICENSE
license_name: kwaipilot-license
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Kwaipilot/KAT-V1-40B
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KAT-V1-40B-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/KAT-V1-40B-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ1_S.gguf) | i1-IQ1_S | 9.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ1_M.gguf) | i1-IQ1_M | 9.8 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.2 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.3 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_S.gguf) | i1-IQ2_S | 12.9 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_M.gguf) | i1-IQ2_M | 14.0 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.3 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q2_K.gguf) | i1-Q2_K | 15.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 16.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 17.0 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_S.gguf) | i1-IQ3_S | 18.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_M.gguf) | i1-IQ3_M | 18.4 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 19.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 21.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.0 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_0.gguf) | i1-Q4_0 | 23.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 23.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 24.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_1.gguf) | i1-Q4_1 | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 28.1 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 28.9 | |
| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q6_K.gguf) | i1-Q6_K | 33.4 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->

3
imatrix.dat Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e5a7a579c24c7969abb5f6e39a09e0490b22d6e50c05f7aeafbeff5d64108000
size 18696365