commit a6c668253582aa86f5404c77d7f02924012bf410 Author: ModelHub XC Date: Mon Oct 19 14:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..12f66d9 --- /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 +Wukong-Phi-3-Instruct-Ablated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Wukong-Phi-3-Instruct-Ablated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..995b91e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: RESMPDEV/Wukong-Phi-3-Instruct-Ablated +datasets: +- cognitivecomputations/Dolphin-2.9 +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/RESMPDEV/Wukong-Phi-3-Instruct-Ablated + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-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/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Wukong-Phi-3-Instruct-Ablated-GGUF/resolve/main/Wukong-Phi-3-Instruct-Ablated.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. + + diff --git a/Wukong-Phi-3-Instruct-Ablated.IQ4_XS.gguf b/Wukong-Phi-3-Instruct-Ablated.IQ4_XS.gguf new file mode 100644 index 0000000..723c39e --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe909172f0d668d2ca5cc8f97e424bf722eae76e42561fac63cc57fa77f93df2 +size 2075581408 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q2_K.gguf b/Wukong-Phi-3-Instruct-Ablated.Q2_K.gguf new file mode 100644 index 0000000..be3cfc9 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7fa4d1cd648e09a25b948e172fd021bbe0dde8ca3cf00b6cfac223c22deba8 +size 1416204256 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q3_K_L.gguf b/Wukong-Phi-3-Instruct-Ablated.Q3_K_L.gguf new file mode 100644 index 0000000..315f2b4 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f3b9bf78a3572e543679a650f49fce2adb02669d0ed5278ebb3db2d4f02acd +size 2087597536 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q3_K_M.gguf b/Wukong-Phi-3-Instruct-Ablated.Q3_K_M.gguf new file mode 100644 index 0000000..2846755 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ebc0a105148f12ae95d429269558755fffd325bd2b229c78b28a1b562598ae +size 1955476960 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q3_K_S.gguf b/Wukong-Phi-3-Instruct-Ablated.Q3_K_S.gguf new file mode 100644 index 0000000..66f1541 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab938f011089fe7ac44ea6a84b3dc616ab484395ab97b1f1d3a17e99ba78f84 +size 1681798624 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q4_K_M.gguf b/Wukong-Phi-3-Instruct-Ablated.Q4_K_M.gguf new file mode 100644 index 0000000..2a94702 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b3eb4c0991405edbd0dffe5658285560d05a0010f9f8df8d4e96ba32da25b7 +size 2393232352 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q4_K_S.gguf b/Wukong-Phi-3-Instruct-Ablated.Q4_K_S.gguf new file mode 100644 index 0000000..80bda4c --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1459c4e3dc270e38e96368fb1679cc726c6f137dc74f866b1d35232c95f8bd3 +size 2188760032 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q5_K_M.gguf b/Wukong-Phi-3-Instruct-Ablated.Q5_K_M.gguf new file mode 100644 index 0000000..f74d482 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf199c53c64b65e0e95a475ecd6b037354446ce124ce5a80914107b9d3ae5f0 +size 2815276000 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q5_K_S.gguf b/Wukong-Phi-3-Instruct-Ablated.Q5_K_S.gguf new file mode 100644 index 0000000..d896c4b --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc814cd51b9835a333e53cd98c59ba148f36a7adcb10e5052716f515c1fe4de +size 2641474528 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q6_K.gguf b/Wukong-Phi-3-Instruct-Ablated.Q6_K.gguf new file mode 100644 index 0000000..aec2388 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00332238c7133e8f02fc0331623a06ba710f476e4e788ce35effd5861b521837 +size 3135853024 diff --git a/Wukong-Phi-3-Instruct-Ablated.Q8_0.gguf b/Wukong-Phi-3-Instruct-Ablated.Q8_0.gguf new file mode 100644 index 0000000..39d6469 --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4355a87f7209dcb31d1c911ed2dfc74ceac2aa99167a704d3bb6feeda0b4da96 +size 4061222368 diff --git a/Wukong-Phi-3-Instruct-Ablated.f16.gguf b/Wukong-Phi-3-Instruct-Ablated.f16.gguf new file mode 100644 index 0000000..11061bf --- /dev/null +++ b/Wukong-Phi-3-Instruct-Ablated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d951fb463eb4e03664ee0082a3605d4d1c28887b6732813752fda74ea6a500 +size 7643297248