commit cd0f9c3c37fbd2f5a3dcfde067aedc761091d2ef Author: ModelHub XC Date: Mon Jun 1 09:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9996f68 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Phi-3-mini-4k-instruct-LASER.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.f16.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-LASER.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-3-mini-4k-instruct-LASER.IQ3_M.gguf b/Phi-3-mini-4k-instruct-LASER.IQ3_M.gguf new file mode 100644 index 0000000..5e82d41 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4690ab536b3898e3b0d227937b3508a22d83e919f19cd05000656299eb44f2a +size 1855599264 diff --git a/Phi-3-mini-4k-instruct-LASER.IQ3_S.gguf b/Phi-3-mini-4k-instruct-LASER.IQ3_S.gguf new file mode 100644 index 0000000..11a91b2 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254a16b5be3db9ccbcc5acd2599ba7f5c880ccd8ce8cfbc9d31d03dbcfa207bc +size 1681797792 diff --git a/Phi-3-mini-4k-instruct-LASER.IQ3_XS.gguf b/Phi-3-mini-4k-instruct-LASER.IQ3_XS.gguf new file mode 100644 index 0000000..29f12fe --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ee70302befc00bee7face46465e3c7560b63d95304e60f37d9c69cc537ff66 +size 1625174688 diff --git a/Phi-3-mini-4k-instruct-LASER.IQ4_XS.gguf b/Phi-3-mini-4k-instruct-LASER.IQ4_XS.gguf new file mode 100644 index 0000000..5781711 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5188ef560d6cfe05228eb57897b09c295a23a627a313e29c33957212cbc279 +size 2075580576 diff --git a/Phi-3-mini-4k-instruct-LASER.Q2_K.gguf b/Phi-3-mini-4k-instruct-LASER.Q2_K.gguf new file mode 100644 index 0000000..f7b9fa0 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80d5eadfe025215a710e8fe3ac582058e44e74f1b0bf9080beee8c1963080b5 +size 1416203424 diff --git a/Phi-3-mini-4k-instruct-LASER.Q3_K_L.gguf b/Phi-3-mini-4k-instruct-LASER.Q3_K_L.gguf new file mode 100644 index 0000000..9bd01b2 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72bf9e61378f73321b0e35162b971a339edc3974a6993e0026e9701acdadc142 +size 2087596704 diff --git a/Phi-3-mini-4k-instruct-LASER.Q3_K_M.gguf b/Phi-3-mini-4k-instruct-LASER.Q3_K_M.gguf new file mode 100644 index 0000000..aeb33f0 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7c563eda63ce433810d86e9e79d70d4f3da304afe879f4d5710897340a44d5 +size 1955476128 diff --git a/Phi-3-mini-4k-instruct-LASER.Q3_K_S.gguf b/Phi-3-mini-4k-instruct-LASER.Q3_K_S.gguf new file mode 100644 index 0000000..112dcb7 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa53932ace19e4af33f9714c5714cf64de97b098f8076f09ed0028b414929a55 +size 1681797792 diff --git a/Phi-3-mini-4k-instruct-LASER.Q4_K_M.gguf b/Phi-3-mini-4k-instruct-LASER.Q4_K_M.gguf new file mode 100644 index 0000000..05694b3 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9caf1c8768fe538dc852cbdbcb40118dc90963ba052286d5eb129685559d6b2 +size 2393231520 diff --git a/Phi-3-mini-4k-instruct-LASER.Q4_K_S.gguf b/Phi-3-mini-4k-instruct-LASER.Q4_K_S.gguf new file mode 100644 index 0000000..4ec4831 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6ca10653f7e206818bbedd6dcb9114e8f9095a9fac6c9822f9de234df1e7ff +size 2188759200 diff --git a/Phi-3-mini-4k-instruct-LASER.Q5_K_M.gguf b/Phi-3-mini-4k-instruct-LASER.Q5_K_M.gguf new file mode 100644 index 0000000..a8bcfb1 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ad4e7879e6d076f78848abe723874572e90db25f4d7943feb4919c658e9d9c +size 2815275168 diff --git a/Phi-3-mini-4k-instruct-LASER.Q5_K_S.gguf b/Phi-3-mini-4k-instruct-LASER.Q5_K_S.gguf new file mode 100644 index 0000000..32f2a2e --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32637182cc5564df834394051a72715ba58c89ba5a93d0de2ca9e77a20edff3e +size 2641473696 diff --git a/Phi-3-mini-4k-instruct-LASER.Q6_K.gguf b/Phi-3-mini-4k-instruct-LASER.Q6_K.gguf new file mode 100644 index 0000000..434ed6c --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb4fbd2a993b2b33d141b2d42a5753f50f78e5014463a3fca4505cfbfc2d6a8 +size 3135852192 diff --git a/Phi-3-mini-4k-instruct-LASER.Q8_0.gguf b/Phi-3-mini-4k-instruct-LASER.Q8_0.gguf new file mode 100644 index 0000000..1ba7187 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f826023796b0bd5b33f4c5395e144120485277cdba81d2fdaa200b3c6f18db2a +size 4061221536 diff --git a/Phi-3-mini-4k-instruct-LASER.f16.gguf b/Phi-3-mini-4k-instruct-LASER.f16.gguf new file mode 100644 index 0000000..b5a2438 --- /dev/null +++ b/Phi-3-mini-4k-instruct-LASER.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72797e6e3091e9ee671ff9007b23cb9933d85d5593177cff4945c690f8758458 +size 7643296416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..da5eaab --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: TeeZee/Phi-3-mini-4k-instruct-LASER +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/TeeZee/Phi-3-mini-4k-instruct-LASER + + +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/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.IQ3_XS.gguf) | IQ3_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.IQ3_S.gguf) | IQ3_S | 1.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.IQ3_M.gguf) | IQ3_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-LASER-GGUF/resolve/main/Phi-3-mini-4k-instruct-LASER.f16.gguf) | f16 | 7.7 | 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. + +