commit 546aa861e08e0302a9c6986bbd4974bcea35fd0d Author: ModelHub XC Date: Tue Aug 11 19:33:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/krx-qwen2-7b-it-X-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..909a6de --- /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-qwen2-7b-it-X.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.f16.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +krx-qwen2-7b-it-X.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c9780a4 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: 2point5p/krx-qwen2-7b-it-X +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/2point5p/krx-qwen2-7b-it-X + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#krx-qwen2-7b-it-X-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-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/krx-qwen2-7b-it-X-GGUF/resolve/main/krx-qwen2-7b-it-X.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-qwen2-7b-it-X.IQ4_XS.gguf b/krx-qwen2-7b-it-X.IQ4_XS.gguf new file mode 100644 index 0000000..03ad1ea --- /dev/null +++ b/krx-qwen2-7b-it-X.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d919118e699922b507b18b9a807cb15dca67aa9c61a3dc4e046ba50f49a4c9 +size 4250296992 diff --git a/krx-qwen2-7b-it-X.Q2_K.gguf b/krx-qwen2-7b-it-X.Q2_K.gguf new file mode 100644 index 0000000..b3836aa --- /dev/null +++ b/krx-qwen2-7b-it-X.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcda7f0f4f41d9d2cc55768f3870382d056998289e190cace226081112f24b8 +size 3015938720 diff --git a/krx-qwen2-7b-it-X.Q3_K_L.gguf b/krx-qwen2-7b-it-X.Q3_K_L.gguf new file mode 100644 index 0000000..b685b8b --- /dev/null +++ b/krx-qwen2-7b-it-X.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fa2470ed397011233da821521c151bd8165db5dc87c1255fcf0b2529d2d692 +size 4088457888 diff --git a/krx-qwen2-7b-it-X.Q3_K_M.gguf b/krx-qwen2-7b-it-X.Q3_K_M.gguf new file mode 100644 index 0000000..b929098 --- /dev/null +++ b/krx-qwen2-7b-it-X.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658a125a7a20a46c66c629de742aa00fe59ccae26fb714f56bdd7645a2d63458 +size 3808389792 diff --git a/krx-qwen2-7b-it-X.Q3_K_S.gguf b/krx-qwen2-7b-it-X.Q3_K_S.gguf new file mode 100644 index 0000000..d5b8c7f --- /dev/null +++ b/krx-qwen2-7b-it-X.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfcc09308527ab95d7da26f4526f637654d960b071cbafa14f213922f20319c +size 3492367008 diff --git a/krx-qwen2-7b-it-X.Q4_K_M.gguf b/krx-qwen2-7b-it-X.Q4_K_M.gguf new file mode 100644 index 0000000..a18234c --- /dev/null +++ b/krx-qwen2-7b-it-X.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c36fefcff8e08054c2e5f7c0981352b2595fb91d32c71732ee9e5aa044642a5 +size 4683072160 diff --git a/krx-qwen2-7b-it-X.Q4_K_S.gguf b/krx-qwen2-7b-it-X.Q4_K_S.gguf new file mode 100644 index 0000000..c6c27a6 --- /dev/null +++ b/krx-qwen2-7b-it-X.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c373c42a6a0b0d63e2cb19e6d4771b7f60ba3a8fdd0ac3b1bc8b363e6ba8e82 +size 4457767584 diff --git a/krx-qwen2-7b-it-X.Q5_K_M.gguf b/krx-qwen2-7b-it-X.Q5_K_M.gguf new file mode 100644 index 0000000..0001eb0 --- /dev/null +++ b/krx-qwen2-7b-it-X.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06238830b0372fc4cde803a71fd7ebb9b4d6acbd271b5bd60899697a5e8df24e +size 5444829856 diff --git a/krx-qwen2-7b-it-X.Q5_K_S.gguf b/krx-qwen2-7b-it-X.Q5_K_S.gguf new file mode 100644 index 0000000..a69d287 --- /dev/null +++ b/krx-qwen2-7b-it-X.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b67aa69d9ceb9a754a312454aa18e8636ed0a6f758ee8933895703da853d9f +size 5315175072 diff --git a/krx-qwen2-7b-it-X.Q6_K.gguf b/krx-qwen2-7b-it-X.Q6_K.gguf new file mode 100644 index 0000000..a90a01f --- /dev/null +++ b/krx-qwen2-7b-it-X.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403fbb462d34c2e509b4980a6733eef9c1c6ef53a8699ae11ba4f2c27999ee5e +size 6254197408 diff --git a/krx-qwen2-7b-it-X.Q8_0.gguf b/krx-qwen2-7b-it-X.Q8_0.gguf new file mode 100644 index 0000000..95ceb63 --- /dev/null +++ b/krx-qwen2-7b-it-X.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49061637c8af3b4e0d974712c1eebdfeb715a696f37a0fbd594f9e15fe5e9655 +size 8098523808 diff --git a/krx-qwen2-7b-it-X.f16.gguf b/krx-qwen2-7b-it-X.f16.gguf new file mode 100644 index 0000000..686a2dc --- /dev/null +++ b/krx-qwen2-7b-it-X.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f2904eebe542229f34189199198aeefdef86aaeb5c29b0d3bbbbe3716adc39 +size 15237851808