commit 5f5710cc59b99cf549f6de9871149518734abf81 Author: ModelHub XC Date: Sun Oct 18 17:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ORANSight_Phi_Mini_Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a31a7f2 --- /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 +ORANSight_Phi_Mini_Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Phi_Mini_Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ORANSight_Phi_Mini_Instruct.IQ4_XS.gguf b/ORANSight_Phi_Mini_Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..0894167 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd732c3abd0127b0469a14f251b111d38dc1e555644b458c0b59af99c1086d4 +size 2075587456 diff --git a/ORANSight_Phi_Mini_Instruct.Q2_K.gguf b/ORANSight_Phi_Mini_Instruct.Q2_K.gguf new file mode 100644 index 0000000..00b361a --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967ced55513666bbd429ec1ccf850da0ca4c05813beeadaae07e26ad55390e69 +size 1446881152 diff --git a/ORANSight_Phi_Mini_Instruct.Q3_K_L.gguf b/ORANSight_Phi_Mini_Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..ad8ad28 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2941f4b034c4864c700745d3d274decc0b5a4cbe655db4727b10980d5cc7b9 +size 2045136256 diff --git a/ORANSight_Phi_Mini_Instruct.Q3_K_M.gguf b/ORANSight_Phi_Mini_Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..37da183 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6b886fb8349fbb736e062707e4c11c37fc28c5ebbb5f26d72e4460d9769932 +size 1877626240 diff --git a/ORANSight_Phi_Mini_Instruct.Q3_K_S.gguf b/ORANSight_Phi_Mini_Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..04fb6d4 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67d9c223a443f98fb6d01bd3f1356fa82523e4d5f08fb05afcd0546cf18fc63 +size 1681804672 diff --git a/ORANSight_Phi_Mini_Instruct.Q4_K_M.gguf b/ORANSight_Phi_Mini_Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..ff64332 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881253de69f9d082a40a2d1246ee419858abdd9fb132c6d5c23e445d0a703d17 +size 2318920576 diff --git a/ORANSight_Phi_Mini_Instruct.Q4_K_S.gguf b/ORANSight_Phi_Mini_Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..b41ee49 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566e82a81e23798e844c04582d2d5898463992a457a5b0ec4a16c5f88240e771 +size 2193484672 diff --git a/ORANSight_Phi_Mini_Instruct.Q5_K_M.gguf b/ORANSight_Phi_Mini_Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bb6aa35 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e1c3562d62f102f3bf9a57898525153784a821d040d23a75e49aeafb99fc66e +size 2715011968 diff --git a/ORANSight_Phi_Mini_Instruct.Q5_K_S.gguf b/ORANSight_Phi_Mini_Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..b25aea0 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9955d10981161170d1f2f3954a8099a0f3bc468158ccfb6143c162cd92b68312 +size 2641480576 diff --git a/ORANSight_Phi_Mini_Instruct.Q6_K.gguf b/ORANSight_Phi_Mini_Instruct.Q6_K.gguf new file mode 100644 index 0000000..700edfb --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a5941d767ccdaed265acfe8e39dbd92fc703ca4f8d6438ae2a321db0772439 +size 3135859072 diff --git a/ORANSight_Phi_Mini_Instruct.Q8_0.gguf b/ORANSight_Phi_Mini_Instruct.Q8_0.gguf new file mode 100644 index 0000000..ffecf30 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928837ef918c3c26cdb82a4562e5db2b00d2de322737e4d15f90b56f8e0739e5 +size 4061228416 diff --git a/ORANSight_Phi_Mini_Instruct.f16.gguf b/ORANSight_Phi_Mini_Instruct.f16.gguf new file mode 100644 index 0000000..2862260 --- /dev/null +++ b/ORANSight_Phi_Mini_Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35fbb8ae2a1aa0b8379b357e3285e82a5cbdabe33899971e0e539fca14c0b70 +size 7643303296 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2946bd --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: NextGLab/ORANSight_Phi_Mini_Instruct +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/NextGLab/ORANSight_Phi_Mini_Instruct + + +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/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Phi_Mini_Instruct-GGUF/resolve/main/ORANSight_Phi_Mini_Instruct.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. + +