commit 96d25d40fcfcde51fa3b5b994b67625cc20acc71 Author: ModelHub XC Date: Sun Aug 9 01:29:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/krx-q25-7b-sft-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c78ba68 --- /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 +krx-q25-7b-sft-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-sft-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1f385a5 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: lsw0570168/krx-q25-7b-sft-v1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- krx +--- +## About + + + + + + +static quants of https://huggingface.co/lsw0570168/krx-q25-7b-sft-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#krx-q25-7b-sft-v1-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/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-sft-v1-GGUF/resolve/main/krx-q25-7b-sft-v1.f16.gguf) | f16 | 15.3 | 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. + + diff --git a/krx-q25-7b-sft-v1.IQ4_XS.gguf b/krx-q25-7b-sft-v1.IQ4_XS.gguf new file mode 100644 index 0000000..f5a3198 --- /dev/null +++ b/krx-q25-7b-sft-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c3a8fa2e9defbba40599d43d4cecaaa7b08099bacb7df798e75d36f05be487 +size 4250296576 diff --git a/krx-q25-7b-sft-v1.Q2_K.gguf b/krx-q25-7b-sft-v1.Q2_K.gguf new file mode 100644 index 0000000..d606c30 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3efd8649a390537c71af1dafda7ca2b41e52e0e66540ec89bfad409047daaa +size 3015938304 diff --git a/krx-q25-7b-sft-v1.Q3_K_L.gguf b/krx-q25-7b-sft-v1.Q3_K_L.gguf new file mode 100644 index 0000000..4883d59 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eddc7e340a9c5702432a7a2a40ba5f0c4ac9f20ae1cd1ee50064df1cc11f8f1a +size 4088457472 diff --git a/krx-q25-7b-sft-v1.Q3_K_M.gguf b/krx-q25-7b-sft-v1.Q3_K_M.gguf new file mode 100644 index 0000000..b14525a --- /dev/null +++ b/krx-q25-7b-sft-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af10f8384ff2eadb29b7ae7dd00ea017b79ca66a0128356a26c703ad14beb19 +size 3808389376 diff --git a/krx-q25-7b-sft-v1.Q3_K_S.gguf b/krx-q25-7b-sft-v1.Q3_K_S.gguf new file mode 100644 index 0000000..9826d63 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcbbfa49614609eb76b7be3ceefc8df1ba38ae5ea02ab6c4bf283faee7288b46 +size 3492366592 diff --git a/krx-q25-7b-sft-v1.Q4_K_M.gguf b/krx-q25-7b-sft-v1.Q4_K_M.gguf new file mode 100644 index 0000000..e00b63f --- /dev/null +++ b/krx-q25-7b-sft-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebc6455062521065c040515a96c1fa25177f7dacea4a6c3b80523316e20d251 +size 4683071744 diff --git a/krx-q25-7b-sft-v1.Q4_K_S.gguf b/krx-q25-7b-sft-v1.Q4_K_S.gguf new file mode 100644 index 0000000..41e7906 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d614211615a2d1a55306bf9594c50bee8b13c15d7eff68c283ad9dfc5dac56 +size 4457767168 diff --git a/krx-q25-7b-sft-v1.Q5_K_M.gguf b/krx-q25-7b-sft-v1.Q5_K_M.gguf new file mode 100644 index 0000000..9c50b86 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6cc426857ec7bf86e2a6d4235902550e7441d4ccce84e440e0b32dee44298b +size 5444829440 diff --git a/krx-q25-7b-sft-v1.Q5_K_S.gguf b/krx-q25-7b-sft-v1.Q5_K_S.gguf new file mode 100644 index 0000000..f5f5cb4 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13150e7a4994db2800dde28d5ea9d0977bda43409722fc5138d138237b7efe8 +size 5315174656 diff --git a/krx-q25-7b-sft-v1.Q6_K.gguf b/krx-q25-7b-sft-v1.Q6_K.gguf new file mode 100644 index 0000000..0feb87a --- /dev/null +++ b/krx-q25-7b-sft-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2714ec7cad0e934ce1179f023db365b9a873648717b859fc9a332077db6265bc +size 6254196992 diff --git a/krx-q25-7b-sft-v1.Q8_0.gguf b/krx-q25-7b-sft-v1.Q8_0.gguf new file mode 100644 index 0000000..220bb28 --- /dev/null +++ b/krx-q25-7b-sft-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d250e5f9b46e18ee5b44e94275caf0940544edbb396fff15f836fcbb043700d +size 8098523392 diff --git a/krx-q25-7b-sft-v1.f16.gguf b/krx-q25-7b-sft-v1.f16.gguf new file mode 100644 index 0000000..3b49e07 --- /dev/null +++ b/krx-q25-7b-sft-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579ac8f570e62a8bf0439346d94732a43eace5d0f5bc38b3b8e0f50c0a23f696 +size 15237851392