commit c743bdba1dc19c80f5be6869bb63da48ff3f0414 Author: ModelHub XC Date: Sun Jun 14 00:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/krx-q25-7b-base-v3.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab954e7 --- /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-base-v3.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.f16.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-q25-7b-base-v3.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e5f5a23 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: lsw0570168/krx-q25-7b-base-v3.3 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/lsw0570168/krx-q25-7b-base-v3.3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#krx-q25-7b-base-v3.3-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-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/krx-q25-7b-base-v3.3-GGUF/resolve/main/krx-q25-7b-base-v3.3.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-base-v3.3.IQ4_XS.gguf b/krx-q25-7b-base-v3.3.IQ4_XS.gguf new file mode 100644 index 0000000..7d8ef46 --- /dev/null +++ b/krx-q25-7b-base-v3.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab0805c6a4039418fd888d40943446c9c33e27930d43104a58149ea88c3fbe2 +size 4250296800 diff --git a/krx-q25-7b-base-v3.3.Q2_K.gguf b/krx-q25-7b-base-v3.3.Q2_K.gguf new file mode 100644 index 0000000..ed3de04 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:326d809c24b24c055d7a7ec45acedfc07aa9e3db884c0cefb5d690cd6e3b78e0 +size 3015938528 diff --git a/krx-q25-7b-base-v3.3.Q3_K_L.gguf b/krx-q25-7b-base-v3.3.Q3_K_L.gguf new file mode 100644 index 0000000..910e4cd --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6f9b458f8134d7b95275cc89e3c6a543874317dcfea87c9acec357b37e03b4 +size 4088457696 diff --git a/krx-q25-7b-base-v3.3.Q3_K_M.gguf b/krx-q25-7b-base-v3.3.Q3_K_M.gguf new file mode 100644 index 0000000..bed66d6 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d17111753f9cbcf2be5ed304d8889cdc62beb5e04a9ec9a00178ea093cafc7e +size 3808389600 diff --git a/krx-q25-7b-base-v3.3.Q3_K_S.gguf b/krx-q25-7b-base-v3.3.Q3_K_S.gguf new file mode 100644 index 0000000..c813641 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4722299adbf823dbb26d24909e3eb1e8e8802928ff81014e85cb6c89f8059f +size 3492366816 diff --git a/krx-q25-7b-base-v3.3.Q4_K_M.gguf b/krx-q25-7b-base-v3.3.Q4_K_M.gguf new file mode 100644 index 0000000..9f07a9c --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f68507217ea5d22847248f56475f4d847e4bc497fde9aed129241b722c2d28 +size 4683071968 diff --git a/krx-q25-7b-base-v3.3.Q4_K_S.gguf b/krx-q25-7b-base-v3.3.Q4_K_S.gguf new file mode 100644 index 0000000..e0a3078 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590791cbd13b9e4c4e126bed61b733e867fa58d8cf6cd943bd7e59c5b434bac6 +size 4457767392 diff --git a/krx-q25-7b-base-v3.3.Q5_K_M.gguf b/krx-q25-7b-base-v3.3.Q5_K_M.gguf new file mode 100644 index 0000000..3a55c2a --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3aeeced0c7a7ca891c7ac55f1e7102bb69c7a47716dc029eeeeb57001e2c125 +size 5444829664 diff --git a/krx-q25-7b-base-v3.3.Q5_K_S.gguf b/krx-q25-7b-base-v3.3.Q5_K_S.gguf new file mode 100644 index 0000000..4dfb867 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe83efdc5b8a23ed47f45eb5c0a1397883046009896014e886af2566ca1b968f +size 5315174880 diff --git a/krx-q25-7b-base-v3.3.Q6_K.gguf b/krx-q25-7b-base-v3.3.Q6_K.gguf new file mode 100644 index 0000000..4525a87 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5f528107d5f0851e0afef667ca42f3085a97fb1b0d513bcda6a710900b7aa5 +size 6254197216 diff --git a/krx-q25-7b-base-v3.3.Q8_0.gguf b/krx-q25-7b-base-v3.3.Q8_0.gguf new file mode 100644 index 0000000..13243a5 --- /dev/null +++ b/krx-q25-7b-base-v3.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6cec7673b89f6673649a3ca2cdcf122608ce6533fca414896a324269bc92d2 +size 8098523616 diff --git a/krx-q25-7b-base-v3.3.f16.gguf b/krx-q25-7b-base-v3.3.f16.gguf new file mode 100644 index 0000000..bf70a9e --- /dev/null +++ b/krx-q25-7b-base-v3.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348b3e2d9bf4585757bce0a6d97e08ede3126fc1c7754ab1ff296644866fce00 +size 15237851616