commit 44a429b08d8c2e1b441d1e6e1596a87e30e777b5 Author: ModelHub XC Date: Sun Apr 12 08:59:56 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/phi-1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5aa84a6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d6f0135 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: microsoft/phi-1 +language: +- en +library_name: transformers +license: mit +license_link: https://huggingface.co/microsoft/phi-1/resolve/main/LICENSE +quantized_by: mradermacher +tags: +- code +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/microsoft/phi-1 + + +static quants are available at https://huggingface.co/mradermacher/phi-1-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-1-i1-GGUF/resolve/main/phi-1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ3_S.gguf) | i1-IQ3_S | 0.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q4_1.gguf) | i1-Q4_1 | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/phi-1-i1-GGUF/resolve/main/phi-1.i1-Q6_K.gguf) | i1-Q6_K | 1.3 | practically like static Q6_K | + +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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..d0eb54d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b8ecf3fd6488dd7f195437755a8df740912ef5f2c406ae69d100d2ca794e08d +size 1774223 diff --git a/phi-1.i1-IQ1_M.gguf b/phi-1.i1-IQ1_M.gguf new file mode 100644 index 0000000..cf21c0e --- /dev/null +++ b/phi-1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7cb2b81bba13c8b2e24cf04f7b53b9215a510b3acc1f6a02dee46cc013de38 +size 395376192 diff --git a/phi-1.i1-IQ1_S.gguf b/phi-1.i1-IQ1_S.gguf new file mode 100644 index 0000000..e0cf9e2 --- /dev/null +++ b/phi-1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02591fd2d17ad4677e7371501c50b1aec4325c93283d13053a998e7e403bfbeb +size 372962880 diff --git a/phi-1.i1-IQ2_M.gguf b/phi-1.i1-IQ2_M.gguf new file mode 100644 index 0000000..81477f0 --- /dev/null +++ b/phi-1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d07475f9f7d6bbbccd937ed8ceb9e356d175215c2ea79369d65f1c2ae4189f +size 535787072 diff --git a/phi-1.i1-IQ2_S.gguf b/phi-1.i1-IQ2_S.gguf new file mode 100644 index 0000000..1d335c4 --- /dev/null +++ b/phi-1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc475197bb67b1087176a3c1fceaff13a03fbf528f5b7fd7e88853535e1df8a +size 505902656 diff --git a/phi-1.i1-IQ2_XS.gguf b/phi-1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4a62389 --- /dev/null +++ b/phi-1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a478869d928adc257f150fec2b8df20ef7daf466443d667589f059c1592ea870 +size 465761856 diff --git a/phi-1.i1-IQ2_XXS.gguf b/phi-1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4d4ad4e --- /dev/null +++ b/phi-1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8a18b3f5e6bcbab0ae81f611c17d75a0ec9595c20bd03d4415a56c5734bc46 +size 432731712 diff --git a/phi-1.i1-IQ3_M.gguf b/phi-1.i1-IQ3_M.gguf new file mode 100644 index 0000000..560ec28 --- /dev/null +++ b/phi-1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebb6c9a2326d6d86106da34f9f1f1d92efe30ca0f28ea071823b59eded47307d +size 687732288 diff --git a/phi-1.i1-IQ3_S.gguf b/phi-1.i1-IQ3_S.gguf new file mode 100644 index 0000000..967c79b --- /dev/null +++ b/phi-1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4efcc3214ff42a7240452081b4aebb1ec474b485e62c6ccfe5b21e14aabbc30d +size 654308928 diff --git a/phi-1.i1-IQ3_XS.gguf b/phi-1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4418739 --- /dev/null +++ b/phi-1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffed77771342f30159ffc6a113d27e793f99b9778656893e6403b47534c88d03 +size 630715968 diff --git a/phi-1.i1-IQ3_XXS.gguf b/phi-1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e420a81 --- /dev/null +++ b/phi-1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1445a497adb7e30a586d33d8d8252e7652b30916bd1bd95e7d6ea89e998c9db +size 575895104 diff --git a/phi-1.i1-IQ4_NL.gguf b/phi-1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..0562067 --- /dev/null +++ b/phi-1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e034fc929624b18cda2f53e74fa6369c2d0a1ef0906b46b64723e4cc5ed56bca +size 828667456 diff --git a/phi-1.i1-IQ4_XS.gguf b/phi-1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..32429cd --- /dev/null +++ b/phi-1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01aad97636a782b6fff4da2a1ebe2058d1d382a45f31d6add02f4aa73e487dce +size 787641920 diff --git a/phi-1.i1-Q2_K.gguf b/phi-1.i1-Q2_K.gguf new file mode 100644 index 0000000..fa2068c --- /dev/null +++ b/phi-1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e329aafda077fe75e5b10fb90755b003eb19a8a0de5ebdc3fbbf891aae3a8f +size 582317632 diff --git a/phi-1.i1-Q2_K_S.gguf b/phi-1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7786c39 --- /dev/null +++ b/phi-1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c132aab37e3552887ddd6d68314bac180150af9d1c4cb84541ce3b9899770771 +size 532772416 diff --git a/phi-1.i1-Q3_K_L.gguf b/phi-1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1f7b340 --- /dev/null +++ b/phi-1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40eb89edabc87574056f2081c512769d2bcc073ef28f07d95dab71b1d69ebc11 +size 810022464 diff --git a/phi-1.i1-Q3_K_M.gguf b/phi-1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..47102cf --- /dev/null +++ b/phi-1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30aa03324334f35203c91da942edbf5ff4e33edd681169977d7ee91176280ffb +size 737670720 diff --git a/phi-1.i1-Q3_K_S.gguf b/phi-1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..982f1e6 --- /dev/null +++ b/phi-1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9badf884ca3ac143586d17f0203961bb232cbfb2692e359605b1a6f92ebbb5a8 +size 654308928 diff --git a/phi-1.i1-Q4_0.gguf b/phi-1.i1-Q4_0.gguf new file mode 100644 index 0000000..5395e06 --- /dev/null +++ b/phi-1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57127b96d2e7965a64fa04aaa580af17215d504c2fa64c1c8d252e49d55ee352 +size 831813184 diff --git a/phi-1.i1-Q4_1.gguf b/phi-1.i1-Q4_1.gguf new file mode 100644 index 0000000..7fc0efd --- /dev/null +++ b/phi-1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9d1f549969475e5b0e116cb89788453d444352aabbd2a58222266e468bb63df +size 910718528 diff --git a/phi-1.i1-Q4_K_M.gguf b/phi-1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2d4d7e6 --- /dev/null +++ b/phi-1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a73bedcd6641c4fc5352bfd810c1d88e1131ee345941875d304db031cac3314 +size 893548096 diff --git a/phi-1.i1-Q4_K_S.gguf b/phi-1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3779f20 --- /dev/null +++ b/phi-1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327ac6b4dba0dff87d464e4c2fe9cfdfc599db6cd89c7d7ec9e03c024e883d08 +size 837056064 diff --git a/phi-1.i1-Q5_K_M.gguf b/phi-1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..327d432 --- /dev/null +++ b/phi-1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c1d53120e75033920fc2f22cea265a168b4c99a5c670f266e340cfd37a8762 +size 1026192960 diff --git a/phi-1.i1-Q5_K_S.gguf b/phi-1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0bb8628 --- /dev/null +++ b/phi-1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8014cfbfc9e01879318824c7d9e408dd51aa6fdf0c7c78d2312f207e6f691845 +size 992769600 diff --git a/phi-1.i1-Q6_K.gguf b/phi-1.i1-Q6_K.gguf new file mode 100644 index 0000000..caa4751 --- /dev/null +++ b/phi-1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458966a2685184c26c57331318ed1c4d55ebbe14e93608df4a61f2314aad8f93 +size 1167128128