commit cfac949cf6028ed9294220f3a13909c47800bb1c Author: ModelHub XC Date: Thu May 14 03:49:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Experiment28M7_Inex16Calme-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fe1e70d --- /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_Inex16Calme.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.f16.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Experiment28M7_Inex16Calme.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Experiment28M7_Inex16Calme.IQ4_XS.gguf b/Experiment28M7_Inex16Calme.IQ4_XS.gguf new file mode 100644 index 0000000..462a7e9 --- /dev/null +++ b/Experiment28M7_Inex16Calme.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11b81a4cc35ec123069733dee03a7f1df7bee5d2dce35f7c8a363238b8aa967 +size 3944389792 diff --git a/Experiment28M7_Inex16Calme.Q2_K.gguf b/Experiment28M7_Inex16Calme.Q2_K.gguf new file mode 100644 index 0000000..78c2b85 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04b30dd1e189e84ba7e3b70f340ba0aba0acbbc66fe67362bd5133e482a4bea +size 2719243424 diff --git a/Experiment28M7_Inex16Calme.Q3_K_L.gguf b/Experiment28M7_Inex16Calme.Q3_K_L.gguf new file mode 100644 index 0000000..46cdd3a --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698fc13cac78d505d6f6b06e858093342f3be66b11d54a1821b5f370e8a807e1 +size 3822025888 diff --git a/Experiment28M7_Inex16Calme.Q3_K_M.gguf b/Experiment28M7_Inex16Calme.Q3_K_M.gguf new file mode 100644 index 0000000..bfc30d4 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9868d9fdcc3bbb7bbc0e6f9808e7cec82d7f0d8f9386fc78ec57026943d60c +size 3518987424 diff --git a/Experiment28M7_Inex16Calme.Q3_K_S.gguf b/Experiment28M7_Inex16Calme.Q3_K_S.gguf new file mode 100644 index 0000000..6e38b76 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b87d6439aa29ae5e435bb6bd1a782954d7931653c2f0479ef316ae718b66793 +size 3164568736 diff --git a/Experiment28M7_Inex16Calme.Q4_K_M.gguf b/Experiment28M7_Inex16Calme.Q4_K_M.gguf new file mode 100644 index 0000000..a17c758 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77796b5fd14b0bf376d484111a2f96a1a200371f79164c9e299bfef6d67643c1 +size 4368440480 diff --git a/Experiment28M7_Inex16Calme.Q4_K_S.gguf b/Experiment28M7_Inex16Calme.Q4_K_S.gguf new file mode 100644 index 0000000..c92b616 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c0364402af1ca5412ccba550a8c9e808b329573faa5bec547903cc02654055 +size 4140375200 diff --git a/Experiment28M7_Inex16Calme.Q5_K_M.gguf b/Experiment28M7_Inex16Calme.Q5_K_M.gguf new file mode 100644 index 0000000..aade0c8 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ed77ce5858c87e813750146542dac481905fad107e02d583bf16b9ccd7a784 +size 5131410592 diff --git a/Experiment28M7_Inex16Calme.Q5_K_S.gguf b/Experiment28M7_Inex16Calme.Q5_K_S.gguf new file mode 100644 index 0000000..86c0fff --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a105034e8f136dfa9a5a2a7a7ffa95a44da7f5ea54f34a1c73680b81a0a241 +size 4997717152 diff --git a/Experiment28M7_Inex16Calme.Q6_K.gguf b/Experiment28M7_Inex16Calme.Q6_K.gguf new file mode 100644 index 0000000..8fd29f9 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7cad29f0efbeb78dca0de7b24a92102568deb97ae9500a7dbbf7f18336564c5 +size 5942066336 diff --git a/Experiment28M7_Inex16Calme.Q8_0.gguf b/Experiment28M7_Inex16Calme.Q8_0.gguf new file mode 100644 index 0000000..c5a1ed7 --- /dev/null +++ b/Experiment28M7_Inex16Calme.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573790e4f4906d70ed21977209397ece876af9247f405c112f3ace9056b896ed +size 7695858848 diff --git a/Experiment28M7_Inex16Calme.f16.gguf b/Experiment28M7_Inex16Calme.f16.gguf new file mode 100644 index 0000000..ba1fad7 --- /dev/null +++ b/Experiment28M7_Inex16Calme.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3714b35f0c603ec5a8419db22900084a8dee9793efa3afecd410284ef33f2380 +size 14484733088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4415956 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: MaziyarPanahi/Experiment28M7_Inex16Calme +language: +- en +library_name: transformers +license: apache-2.0 +model_creator: MaziyarPanahi +model_name: Experiment28M7_Inex16Calme +quantized_by: mradermacher +tags: +- Safetensors +- text-generation-inference +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/MaziyarPanahi/Experiment28M7_Inex16Calme + + +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_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Experiment28M7_Inex16Calme-GGUF/resolve/main/Experiment28M7_Inex16Calme.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +