commit 3160dc7d5a7d370bb13524782bc448ab8e739d25 Author: ModelHub XC Date: Fri Jun 12 23:16:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KPT-7b-v0.2_stock-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1224511 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +KPT-7b-v0.2_stock.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.f16.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KPT-7b-v0.2_stock.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KPT-7b-v0.2_stock.IQ4_XS.gguf b/KPT-7b-v0.2_stock.IQ4_XS.gguf new file mode 100644 index 0000000..ad95fe9 --- /dev/null +++ b/KPT-7b-v0.2_stock.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0b07f6b79406a4d3e2c646da9a6f00d44b566cfc3f04a47acc06c46c5127ef +size 3944390720 diff --git a/KPT-7b-v0.2_stock.Q2_K.gguf b/KPT-7b-v0.2_stock.Q2_K.gguf new file mode 100644 index 0000000..52888df --- /dev/null +++ b/KPT-7b-v0.2_stock.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7cb1b5eeb362c4cfe568cb4e71394e74f80d386a19b126f44c97285af478b4 +size 2719244352 diff --git a/KPT-7b-v0.2_stock.Q3_K_L.gguf b/KPT-7b-v0.2_stock.Q3_K_L.gguf new file mode 100644 index 0000000..90dea3c --- /dev/null +++ b/KPT-7b-v0.2_stock.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619dec57499e356ff7ea5fc196c7e555ac8bb49113c4a4b1bd588cd2c9ca06c5 +size 3822026816 diff --git a/KPT-7b-v0.2_stock.Q3_K_M.gguf b/KPT-7b-v0.2_stock.Q3_K_M.gguf new file mode 100644 index 0000000..748c1cb --- /dev/null +++ b/KPT-7b-v0.2_stock.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faeb321de4910eddfb5f65eda26de8bad44614eb7c786dc4a7255aeea83ce2f2 +size 3518988352 diff --git a/KPT-7b-v0.2_stock.Q3_K_S.gguf b/KPT-7b-v0.2_stock.Q3_K_S.gguf new file mode 100644 index 0000000..9dd59ed --- /dev/null +++ b/KPT-7b-v0.2_stock.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5cb9a07461dfca9f3fe24b968ae13e90abcdbffeaf54ced5ff9ac8e4c8162a +size 3164569664 diff --git a/KPT-7b-v0.2_stock.Q4_K_M.gguf b/KPT-7b-v0.2_stock.Q4_K_M.gguf new file mode 100644 index 0000000..2b52d5f --- /dev/null +++ b/KPT-7b-v0.2_stock.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f1c466c4392fd7f54c927ee803f15a38ba0312e339788bbd03664de88847f7 +size 4368441408 diff --git a/KPT-7b-v0.2_stock.Q4_K_S.gguf b/KPT-7b-v0.2_stock.Q4_K_S.gguf new file mode 100644 index 0000000..9bbf607 --- /dev/null +++ b/KPT-7b-v0.2_stock.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94c04e2d8611ffc7e50115ca32dfe947884a62564bf22d49ea60d5bc7ef87ccf +size 4140376128 diff --git a/KPT-7b-v0.2_stock.Q5_K_M.gguf b/KPT-7b-v0.2_stock.Q5_K_M.gguf new file mode 100644 index 0000000..7dfc5e9 --- /dev/null +++ b/KPT-7b-v0.2_stock.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39d76b717339256908b438976752c957f644cbb0e3bc200cb0d26c17e6b23d5 +size 5131411520 diff --git a/KPT-7b-v0.2_stock.Q5_K_S.gguf b/KPT-7b-v0.2_stock.Q5_K_S.gguf new file mode 100644 index 0000000..2d46a9a --- /dev/null +++ b/KPT-7b-v0.2_stock.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6017806698c3573f2b7857866bd8e296e63f576d5aedf76f5077a422b31c4173 +size 4997718080 diff --git a/KPT-7b-v0.2_stock.Q6_K.gguf b/KPT-7b-v0.2_stock.Q6_K.gguf new file mode 100644 index 0000000..bae61b8 --- /dev/null +++ b/KPT-7b-v0.2_stock.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0101567ca825c489467542de156de999ff15c6a77b9390cab54cf202f5fb8326 +size 5942067264 diff --git a/KPT-7b-v0.2_stock.Q8_0.gguf b/KPT-7b-v0.2_stock.Q8_0.gguf new file mode 100644 index 0000000..41a4ed8 --- /dev/null +++ b/KPT-7b-v0.2_stock.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5535fc9f187b3dc3fb09e2731cf7898a6f3b2a9325fb7e6e8a5feec2e7c0b17 +size 7695859776 diff --git a/KPT-7b-v0.2_stock.f16.gguf b/KPT-7b-v0.2_stock.f16.gguf new file mode 100644 index 0000000..8043e6d --- /dev/null +++ b/KPT-7b-v0.2_stock.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e29e559575470814d4aa9b08a50c14bb489fcf64a7f613d559a08d2a819f81 +size 14484734016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..607a2c3 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: kainatq/KPT-7b-v0.2_stock +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/kainatq/KPT-7b-v0.2_stock + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KPT-7b-v0.2_stock-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KPT-7b-v0.2_stock-GGUF/resolve/main/KPT-7b-v0.2_stock.f16.gguf) | f16 | 14.6 | 16 bpw, overkill | + +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. + +