commit 02c325c3f4792c8e9778c0f3cd0923468a1be7bd Author: ModelHub XC Date: Fri May 8 22:29:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mental_Qwen3-8B-mix-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c57e6ee --- /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 +Mental_Qwen3-8B-mix-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mental_Qwen3-8B-mix-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mental_Qwen3-8B-mix-sft.IQ4_XS.gguf b/Mental_Qwen3-8B-mix-sft.IQ4_XS.gguf new file mode 100644 index 0000000..4d05526 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1602d49f54d5658aa4e82e91a99d018ec327fd5c6e69d54c41a967582656383 +size 4593296704 diff --git a/Mental_Qwen3-8B-mix-sft.Q2_K.gguf b/Mental_Qwen3-8B-mix-sft.Q2_K.gguf new file mode 100644 index 0000000..b0fad6e --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a59996ffab0b2197aadb10b6af91281c7e996c447539baea6dd08e287f019d +size 3281732928 diff --git a/Mental_Qwen3-8B-mix-sft.Q3_K_L.gguf b/Mental_Qwen3-8B-mix-sft.Q3_K_L.gguf new file mode 100644 index 0000000..9f6c355 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b9b50a57a0298760f897ee14484df3aa34029c2b1164f28d851cdf37c1c38f +size 4431394112 diff --git a/Mental_Qwen3-8B-mix-sft.Q3_K_M.gguf b/Mental_Qwen3-8B-mix-sft.Q3_K_M.gguf new file mode 100644 index 0000000..a752c2f --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ccfa5c314a29acc0508188f3ff121c53515adf5909b0cc65aa292703ca1daab +size 4124161344 diff --git a/Mental_Qwen3-8B-mix-sft.Q3_K_S.gguf b/Mental_Qwen3-8B-mix-sft.Q3_K_S.gguf new file mode 100644 index 0000000..92ff452 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418c4ae2c07b83a5552d4abd86cdeca3bbf63f8d512b4e8f6368c93a9cdd87cf +size 3769611584 diff --git a/Mental_Qwen3-8B-mix-sft.Q4_K_M.gguf b/Mental_Qwen3-8B-mix-sft.Q4_K_M.gguf new file mode 100644 index 0000000..d7ea407 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea0a888bda01d16cf231100aeaa71c4ca359cee39394990e32116eea9c4518d +size 5027784000 diff --git a/Mental_Qwen3-8B-mix-sft.Q4_K_S.gguf b/Mental_Qwen3-8B-mix-sft.Q4_K_S.gguf new file mode 100644 index 0000000..4275b1d --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:081821f6d9dd2fc1965d119330d6806b8d797b778b8feafa0f55ebbbb13ff652 +size 4802012480 diff --git a/Mental_Qwen3-8B-mix-sft.Q5_K_M.gguf b/Mental_Qwen3-8B-mix-sft.Q5_K_M.gguf new file mode 100644 index 0000000..90a0cd7 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656b5ba2a51d3085c9cba5fe5ef836d520bcc0bb5da59545c28edefd501a7d07 +size 5851112768 diff --git a/Mental_Qwen3-8B-mix-sft.Q5_K_S.gguf b/Mental_Qwen3-8B-mix-sft.Q5_K_S.gguf new file mode 100644 index 0000000..33cd287 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6efb53455751f8f2d40995e7ca95a4aaeb42568ac7aaae8c7e67b7f11fdf725 +size 5720761664 diff --git a/Mental_Qwen3-8B-mix-sft.Q6_K.gguf b/Mental_Qwen3-8B-mix-sft.Q6_K.gguf new file mode 100644 index 0000000..d9afe7d --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4258162dfc11e589de72e61a4f9770c4a3795e5a51b6bc8bff67cd9504870a91 +size 6725899584 diff --git a/Mental_Qwen3-8B-mix-sft.Q8_0.gguf b/Mental_Qwen3-8B-mix-sft.Q8_0.gguf new file mode 100644 index 0000000..1ce11c6 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15145d3800acabca4d1292a26f02b0c1aaaea2332f2073325d8d79bcd898914e +size 8709518656 diff --git a/Mental_Qwen3-8B-mix-sft.f16.gguf b/Mental_Qwen3-8B-mix-sft.f16.gguf new file mode 100644 index 0000000..c873105 --- /dev/null +++ b/Mental_Qwen3-8B-mix-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e932bda9b6fdb37e6b73092026caef5ceb95afe5a333364a67e2c4a47e96712c +size 16388044096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..32dd2be --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: HeAAAAA/Mental_Qwen3-8B-mix-sft +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/HeAAAAA/Mental_Qwen3-8B-mix-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mental_Qwen3-8B-mix-sft-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/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mental_Qwen3-8B-mix-sft-GGUF/resolve/main/Mental_Qwen3-8B-mix-sft.f16.gguf) | f16 | 16.5 | 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. + +