commit 2c2002d09c1175b13cf837d588a83f5213f51bc0 Author: ModelHub XC Date: Wed Sep 23 06:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Not-WizardLM-2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b333c48 --- /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 +Not-WizardLM-2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Not-WizardLM-2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Not-WizardLM-2-7B.IQ4_XS.gguf b/Not-WizardLM-2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..f91905b --- /dev/null +++ b/Not-WizardLM-2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d047de69fae4d2acc16dbba3560f80f77dcb60c8156ce42406321cd9b8813ff5 +size 3944388928 diff --git a/Not-WizardLM-2-7B.Q2_K.gguf b/Not-WizardLM-2-7B.Q2_K.gguf new file mode 100644 index 0000000..edceab3 --- /dev/null +++ b/Not-WizardLM-2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ff761e9d4d2b24d30babeefae9d6842c04275dbc7e2982473f19cfdf5c4b1a +size 2719242560 diff --git a/Not-WizardLM-2-7B.Q3_K_L.gguf b/Not-WizardLM-2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..acbf7b9 --- /dev/null +++ b/Not-WizardLM-2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ead8bbe6543b7046b265ba7781fdc1f48f6576448a666f05d8a8bc44ee91061 +size 3822025024 diff --git a/Not-WizardLM-2-7B.Q3_K_M.gguf b/Not-WizardLM-2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..912e1f4 --- /dev/null +++ b/Not-WizardLM-2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585c1f652fc982fae8bbbb0f5dc98c78206ad92df8af8f33023ad52b7dcdc772 +size 3518986560 diff --git a/Not-WizardLM-2-7B.Q3_K_S.gguf b/Not-WizardLM-2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..c087888 --- /dev/null +++ b/Not-WizardLM-2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03a4316a0db0924348ab11116474dfaa7411a44a80fabf6a8bf47e5576cf2ff +size 3164567872 diff --git a/Not-WizardLM-2-7B.Q4_K_M.gguf b/Not-WizardLM-2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..9de2267 --- /dev/null +++ b/Not-WizardLM-2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98dd2eddbb2491afbbb80a75a075015c15cd12aea89eabff001b9af5c97542cc +size 4368439616 diff --git a/Not-WizardLM-2-7B.Q4_K_S.gguf b/Not-WizardLM-2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..bb6ac1b --- /dev/null +++ b/Not-WizardLM-2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613aa7d86ced448c1cfe26fd363c4a45513d151f427a3c9d1876f74b603d5db4 +size 4140374336 diff --git a/Not-WizardLM-2-7B.Q5_K_M.gguf b/Not-WizardLM-2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..013e754 --- /dev/null +++ b/Not-WizardLM-2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3dcd8c04815b3842b30d9fe6aa471e428a7dda56238623c4de35ac4d28f65f +size 5131409728 diff --git a/Not-WizardLM-2-7B.Q5_K_S.gguf b/Not-WizardLM-2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..c7f56ad --- /dev/null +++ b/Not-WizardLM-2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a8982ecd8d4e4dd22d0018207576e839c6ba114ac459963af715e360060a5e1 +size 4997716288 diff --git a/Not-WizardLM-2-7B.Q6_K.gguf b/Not-WizardLM-2-7B.Q6_K.gguf new file mode 100644 index 0000000..372d65c --- /dev/null +++ b/Not-WizardLM-2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a573977788f9268d6671d89ee0895fdeef0237537f53085254e55ec8c2d746d0 +size 5942065472 diff --git a/Not-WizardLM-2-7B.Q8_0.gguf b/Not-WizardLM-2-7B.Q8_0.gguf new file mode 100644 index 0000000..d0f6bb2 --- /dev/null +++ b/Not-WizardLM-2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6e88da3bb5a97a7692bf1f9b94dd92ec4d07cf20c708e2e4fb5b1507399556 +size 7695857984 diff --git a/Not-WizardLM-2-7B.f16.gguf b/Not-WizardLM-2-7B.f16.gguf new file mode 100644 index 0000000..d1ec2c2 --- /dev/null +++ b/Not-WizardLM-2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44f09906c719998c37489365bb236d6ae1cf5e6162e4d89f8a705b196cd36ad +size 14484732224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f28c71 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: amazingvince/Not-WizardLM-2-7B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/amazingvince/Not-WizardLM-2-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Not-WizardLM-2-7B-i1-GGUF +## 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/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Not-WizardLM-2-7B-GGUF/resolve/main/Not-WizardLM-2-7B.f16.gguf) | f16 | 14.6 | 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. + +