commit 409b257fc288c8b627f38509f38ab7b17b5c56e9 Author: ModelHub XC Date: Tue Jul 21 23:09:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qmerft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fdbf899 --- /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 +Qmerft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qmerft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qmerft.IQ4_XS.gguf b/Qmerft.IQ4_XS.gguf new file mode 100644 index 0000000..948510e --- /dev/null +++ b/Qmerft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7addd0e69aae55b52eaa63e99f4b80c38ffa26b8119b0d1e4864c55b9b0fedfc +size 1026163072 diff --git a/Qmerft.Q2_K.gguf b/Qmerft.Q2_K.gguf new file mode 100644 index 0000000..4e7e2c7 --- /dev/null +++ b/Qmerft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f311bbb2d0dc7eeb12f8361e3e1a6082c60c48961149608f33183375b44b81e +size 752881024 diff --git a/Qmerft.Q3_K_L.gguf b/Qmerft.Q3_K_L.gguf new file mode 100644 index 0000000..e6b1ee9 --- /dev/null +++ b/Qmerft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9567db28821648d375a510d00cae6904f1a0150ae8ea62284ffedfe6fdb9a701 +size 980440960 diff --git a/Qmerft.Q3_K_M.gguf b/Qmerft.Q3_K_M.gguf new file mode 100644 index 0000000..bfb82fc --- /dev/null +++ b/Qmerft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4770311c495d77f5fc2825640b5ff526a973da5223e0c3de453c7e86fd4106d3 +size 924456832 diff --git a/Qmerft.Q3_K_S.gguf b/Qmerft.Q3_K_S.gguf new file mode 100644 index 0000000..1a2a624 --- /dev/null +++ b/Qmerft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b736e887a03e1e62fa1cbd1bb499f6b3ee7b73ca8f271917ea5b80c712c6a9b +size 861222784 diff --git a/Qmerft.Q4_K_M.gguf b/Qmerft.Q4_K_M.gguf new file mode 100644 index 0000000..1261000 --- /dev/null +++ b/Qmerft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ac93be8f36ad60c84c8a416ff10520bc19c28d470b6b2963443f3faa3f39fc +size 1117321600 diff --git a/Qmerft.Q4_K_S.gguf b/Qmerft.Q4_K_S.gguf new file mode 100644 index 0000000..77aaa1f --- /dev/null +++ b/Qmerft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3705894973cdde9e893195812acf9cef27ae40685a656bb8bbeded5c082fe1 +size 1071585664 diff --git a/Qmerft.Q5_K_M.gguf b/Qmerft.Q5_K_M.gguf new file mode 100644 index 0000000..faf89dc --- /dev/null +++ b/Qmerft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04f93ab895f0f9e43a171f55bf83aec529c7b763228ab31c10d30f31772ad85 +size 1285495168 diff --git a/Qmerft.Q5_K_S.gguf b/Qmerft.Q5_K_S.gguf new file mode 100644 index 0000000..bd4b0ea --- /dev/null +++ b/Qmerft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19960a2e7256e304fbe4c10bfb74f38419f501b8c356e9cf489a7d69e328a1ab +size 1259174272 diff --git a/Qmerft.Q6_K.gguf b/Qmerft.Q6_K.gguf new file mode 100644 index 0000000..50cf752 --- /dev/null +++ b/Qmerft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a12fe40505f5ebc2402b2e2623f81f66d7aa002b6c87f909e8d7c7013834cf0 +size 1464179584 diff --git a/Qmerft.Q8_0.gguf b/Qmerft.Q8_0.gguf new file mode 100644 index 0000000..0bacb2b --- /dev/null +++ b/Qmerft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fa1932b7fa12f1ff3cdd40147e2266d779cdda70fc4bf5c4dd8e633ab478f1 +size 1894532992 diff --git a/Qmerft.f16.gguf b/Qmerft.f16.gguf new file mode 100644 index 0000000..2038934 --- /dev/null +++ b/Qmerft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20343d4a1cf9878f72d56cfd9f96cac90aac4f5fdaca389b23ba6bb8aa389e06 +size 3560417152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1983f5d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: sumink/Qmerft +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/sumink/Qmerft + + +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/Qmerft-GGUF/resolve/main/Qmerft.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qmerft-GGUF/resolve/main/Qmerft.f16.gguf) | f16 | 3.7 | 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. + +