commit 5effd8ed3ca1e9a9232a3ba1475eb611887a28f9 Author: ModelHub XC Date: Wed Jul 22 20:23:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4d05a84 --- /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 +Phi-3.5-mini-instruct-3x-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3.5-mini-instruct-3x-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-3.5-mini-instruct-3x-v1.IQ4_XS.gguf b/Phi-3.5-mini-instruct-3x-v1.IQ4_XS.gguf new file mode 100644 index 0000000..c933f13 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b09f7bd30466980240cd8a4bd0c5a6b8bdb043301bae264d8534159972bfe07 +size 2075582048 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q2_K.gguf b/Phi-3.5-mini-instruct-3x-v1.Q2_K.gguf new file mode 100644 index 0000000..5b2f563 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38608ca455e321764f5d924bf968978a0c191e207ac61aadcbb0eb4295e693a +size 1416204896 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q3_K_L.gguf b/Phi-3.5-mini-instruct-3x-v1.Q3_K_L.gguf new file mode 100644 index 0000000..a1ca0c8 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccb4a25b39f2ffd642e36707809904d8b131c56827fa0fbe42fb0ad303b31c7 +size 2087598176 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q3_K_M.gguf b/Phi-3.5-mini-instruct-3x-v1.Q3_K_M.gguf new file mode 100644 index 0000000..8309729 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c5ebe03002323713c5bbdb7cce8a3864efb97c700a771b018024c416607d6c +size 1955477600 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q3_K_S.gguf b/Phi-3.5-mini-instruct-3x-v1.Q3_K_S.gguf new file mode 100644 index 0000000..c8905b0 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14375e262c3aa7147a24a8c0401aa27605a9c1138235c46599602a66e1a715ef +size 1681799264 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q4_K_M.gguf b/Phi-3.5-mini-instruct-3x-v1.Q4_K_M.gguf new file mode 100644 index 0000000..b56aa48 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d04b63a4e66094da0b196bac1532b0c11d57146f7c257baa01dad6f7e6f3678 +size 2393232992 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q4_K_S.gguf b/Phi-3.5-mini-instruct-3x-v1.Q4_K_S.gguf new file mode 100644 index 0000000..171e30b --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5035f277c570070c4e1f9dd03f70f4b2968d110a4bda05e49121fdaba03efa5b +size 2188760672 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q5_K_M.gguf b/Phi-3.5-mini-instruct-3x-v1.Q5_K_M.gguf new file mode 100644 index 0000000..baa1728 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c824cfeffb1282e59ac2d6916ab19551fdcfafeeb8872f69522c56105912d331 +size 2815276640 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q5_K_S.gguf b/Phi-3.5-mini-instruct-3x-v1.Q5_K_S.gguf new file mode 100644 index 0000000..f6a0ad9 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb6e8832280ac744ce960593d8128c8a3d68e4e76faf478eec5c633c232c1ea +size 2641475168 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q6_K.gguf b/Phi-3.5-mini-instruct-3x-v1.Q6_K.gguf new file mode 100644 index 0000000..79d2a0e --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b2efafe25af84d0d724a84747426f9ab5b3df91ccec6c55118636acb620313 +size 3135853664 diff --git a/Phi-3.5-mini-instruct-3x-v1.Q8_0.gguf b/Phi-3.5-mini-instruct-3x-v1.Q8_0.gguf new file mode 100644 index 0000000..3ac881c --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:008b1fccb28f640ac21b34b97ffe0257109490298ef9361110ea7e62447122a6 +size 4061223008 diff --git a/Phi-3.5-mini-instruct-3x-v1.f16.gguf b/Phi-3.5-mini-instruct-3x-v1.f16.gguf new file mode 100644 index 0000000..b1fd5a0 --- /dev/null +++ b/Phi-3.5-mini-instruct-3x-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48961ee57c82ee608c8860fe0a892a3dc183850764d4f5bb1d7e18685542f6cb +size 7643297888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3ebb9ce --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mateussj/Phi-3.5-mini-instruct-3x-v1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mateussj/Phi-3.5-mini-instruct-3x-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Phi-3.5-mini-instruct-3x-v1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-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/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3.5-mini-instruct-3x-v1-GGUF/resolve/main/Phi-3.5-mini-instruct-3x-v1.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. + +