commit 7bc0b20e50c09be758fad11bf6f9d697e5946150 Author: ModelHub XC Date: Thu Oct 15 21:44:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Experiment28M7_Inex12Neural-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..921c689 --- /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 +Experiment28M7_Inex12Neural.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex12Neural.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Experiment28M7_Inex12Neural.IQ4_XS.gguf b/Experiment28M7_Inex12Neural.IQ4_XS.gguf new file mode 100644 index 0000000..d8b23e4 --- /dev/null +++ b/Experiment28M7_Inex12Neural.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:163ad1fce0613d40d9f23c1ebf4f0867361bb99533e983d32df01e12601131f4 +size 3944389792 diff --git a/Experiment28M7_Inex12Neural.Q2_K.gguf b/Experiment28M7_Inex12Neural.Q2_K.gguf new file mode 100644 index 0000000..105c27f --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d58db69be42518169de0bdabfa2a17ff540967a08c9e1ac885ef5426321eb7 +size 2719243424 diff --git a/Experiment28M7_Inex12Neural.Q3_K_L.gguf b/Experiment28M7_Inex12Neural.Q3_K_L.gguf new file mode 100644 index 0000000..9d5e14d --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc32f736cde9edcc9a61e47d49b2ab687db1517371c0605a8fdf0f5d8c8d491 +size 3822025888 diff --git a/Experiment28M7_Inex12Neural.Q3_K_M.gguf b/Experiment28M7_Inex12Neural.Q3_K_M.gguf new file mode 100644 index 0000000..2634b2d --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5456b002a06c37d2d99cbeb8d22d6020ee2c91173e6bb5eafb0ede5b04ef7256 +size 3518987424 diff --git a/Experiment28M7_Inex12Neural.Q3_K_S.gguf b/Experiment28M7_Inex12Neural.Q3_K_S.gguf new file mode 100644 index 0000000..fa8bab1 --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37e41b99d4896101b34a82d15483e5fe56bf51e6fe4884c8b8cc87606b74a4f +size 3164568736 diff --git a/Experiment28M7_Inex12Neural.Q4_K_M.gguf b/Experiment28M7_Inex12Neural.Q4_K_M.gguf new file mode 100644 index 0000000..6a6e8b4 --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7052f6b0b870c56f48ccff32204f3309a2f7bda6e5e212e079348c5c57e74b +size 4368440480 diff --git a/Experiment28M7_Inex12Neural.Q4_K_S.gguf b/Experiment28M7_Inex12Neural.Q4_K_S.gguf new file mode 100644 index 0000000..3dc07a6 --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e85bd5476e5ad406f15ad009b099c2f7f9432c405cba64675630d6a6cdc6b9 +size 4140375200 diff --git a/Experiment28M7_Inex12Neural.Q5_K_M.gguf b/Experiment28M7_Inex12Neural.Q5_K_M.gguf new file mode 100644 index 0000000..60881bd --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39464b7577c685ff20a46cfce6545865832cbc2a4241099e960f265ef5e53b8 +size 5131410592 diff --git a/Experiment28M7_Inex12Neural.Q5_K_S.gguf b/Experiment28M7_Inex12Neural.Q5_K_S.gguf new file mode 100644 index 0000000..40a5dba --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9630c5c074a9e1ff87fe74a39aecd84d4fe298609f1cceaded4aed46ef77d3d +size 4997717152 diff --git a/Experiment28M7_Inex12Neural.Q6_K.gguf b/Experiment28M7_Inex12Neural.Q6_K.gguf new file mode 100644 index 0000000..a53556e --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ace0a447a5b86efdef8ba0bfbda2ca31cdb762a077e391d7891a2982025811 +size 5942066336 diff --git a/Experiment28M7_Inex12Neural.Q8_0.gguf b/Experiment28M7_Inex12Neural.Q8_0.gguf new file mode 100644 index 0000000..221e98e --- /dev/null +++ b/Experiment28M7_Inex12Neural.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab9818e29f295bd66a372e874a774d02319c51ec5871d1331a8496f84b128e7 +size 7695858848 diff --git a/Experiment28M7_Inex12Neural.f16.gguf b/Experiment28M7_Inex12Neural.f16.gguf new file mode 100644 index 0000000..1afc16d --- /dev/null +++ b/Experiment28M7_Inex12Neural.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe19d7cc92b1e5acb8fb4634cb61ebe2e593d5495e24b68d6d75db1d4962828d +size 14484733088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e757b6 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: MaziyarPanahi/Experiment28M7_Inex12Neural +language: +- en +library_name: transformers +license: apache-2.0 +model_creator: MaziyarPanahi +model_name: Experiment28M7_Inex12Neural +quantized_by: mradermacher +tags: +- Safetensors +- text-generation-inference +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/MaziyarPanahi/Experiment28M7_Inex12Neural + + +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/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex12Neural-GGUF/resolve/main/Experiment28M7_Inex12Neural.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. + +