commit 616c6b6035e307961cacbb0c0b999a925b0e9005 Author: ModelHub XC Date: Tue May 5 21:50:41 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/phi-2-super-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef00468 --- /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-2-super.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.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..85d3229 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: abacaj/phi-2-super +language: +- en +library_name: transformers +license: mit +license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- convAI +- conversational +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/abacaj/phi-2-super + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#phi-2-super-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/phi-2-super-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-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ1_M.gguf) | i1-IQ1_M | 0.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ2_M.gguf) | i1-IQ2_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q2_K.gguf) | i1-Q2_K | 1.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ3_S.gguf) | i1-IQ3_S | 1.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ3_M.gguf) | i1-IQ3_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q4_0.gguf) | i1-Q4_0 | 1.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q4_1.gguf) | i1-Q4_1 | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/phi-2-super-i1-GGUF/resolve/main/phi-2-super.i1-Q6_K.gguf) | i1-Q6_K | 2.4 | 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..d3a85e8 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b8ef0dc1c86bf3b75059d0fde97eb2c2c77d312663a005357301b605bad45f +size 2955463 diff --git a/phi-2-super.i1-IQ1_M.gguf b/phi-2-super.i1-IQ1_M.gguf new file mode 100644 index 0000000..a1a6e35 --- /dev/null +++ b/phi-2-super.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b48a4686b1821711c13dfe772c4ea85e354ece1539d1c290cba8b28f8c593490 +size 731865376 diff --git a/phi-2-super.i1-IQ1_S.gguf b/phi-2-super.i1-IQ1_S.gguf new file mode 100644 index 0000000..207d6b1 --- /dev/null +++ b/phi-2-super.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfdfcb2ea44534a232f60aed7cfbd23cf39377ae2fe203a415072ef88900f23 +size 685170976 diff --git a/phi-2-super.i1-IQ2_M.gguf b/phi-2-super.i1-IQ2_M.gguf new file mode 100644 index 0000000..1d818df --- /dev/null +++ b/phi-2-super.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2421ace3b727292654ceb1f4004712c55d6a40ccf685dadb8c3e9ff3da0530ea +size 1015513376 diff --git a/phi-2-super.i1-IQ2_S.gguf b/phi-2-super.i1-IQ2_S.gguf new file mode 100644 index 0000000..c4c9dd3 --- /dev/null +++ b/phi-2-super.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a42946828f6c467cce45bb330bb954a89fe8b16e82438a5d3879f667ee254a9 +size 953254176 diff --git a/phi-2-super.i1-IQ2_XS.gguf b/phi-2-super.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9fb5528 --- /dev/null +++ b/phi-2-super.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa0fe7aa88263861bc26a0bade6a8bf915c184df7d042d1fd64a18897e7024b +size 878502176 diff --git a/phi-2-super.i1-IQ2_XXS.gguf b/phi-2-super.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..979e4d2 --- /dev/null +++ b/phi-2-super.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f627c6ef6ce3141d87001f1b6863793fd6654988c3185520d2c6c4b5ba42b76 +size 809689376 diff --git a/phi-2-super.i1-IQ3_M.gguf b/phi-2-super.i1-IQ3_M.gguf new file mode 100644 index 0000000..78f80a6 --- /dev/null +++ b/phi-2-super.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a421c1d95f03216446b001f469ffc482ca415dca8d8c5c2cc40f7d552d8377 +size 1320460576 diff --git a/phi-2-super.i1-IQ3_S.gguf b/phi-2-super.i1-IQ3_S.gguf new file mode 100644 index 0000000..31dc942 --- /dev/null +++ b/phi-2-super.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e158ef60f1484baef195d134b227ed4920fbfa0f48e9e17c98d1363568db35c2 +size 1250828576 diff --git a/phi-2-super.i1-IQ3_XS.gguf b/phi-2-super.i1-IQ3_XS.gguf new file mode 100644 index 0000000..af9190e --- /dev/null +++ b/phi-2-super.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4e909d7946dea6fe548e8d5abfaa025066be89a60598429bee945c54c7e462 +size 1201676576 diff --git a/phi-2-super.i1-IQ3_XXS.gguf b/phi-2-super.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e216f92 --- /dev/null +++ b/phi-2-super.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec84e4e6f3330d421687920fe0e026c885d5ae69df0c1ecf73200ed15b9a3ecd +size 1099071776 diff --git a/phi-2-super.i1-IQ4_NL.gguf b/phi-2-super.i1-IQ4_NL.gguf new file mode 100644 index 0000000..07d4a4a --- /dev/null +++ b/phi-2-super.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6f6b0425cb9cdda947d5cb11e058a256f94afa9c044ef7313f2f24313d0993 +size 1602470176 diff --git a/phi-2-super.i1-IQ4_XS.gguf b/phi-2-super.i1-IQ4_XS.gguf new file mode 100644 index 0000000..84901f0 --- /dev/null +++ b/phi-2-super.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9d0f824cb6bf2f48592c54d9fd23f803186362b7f164a24f8f48ecb7208b0b8 +size 1519730976 diff --git a/phi-2-super.i1-Q2_K.gguf b/phi-2-super.i1-Q2_K.gguf new file mode 100644 index 0000000..42e3a6b --- /dev/null +++ b/phi-2-super.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8eef08fec0d56c18af5b522a33c771884b8b6fdaf50ed66c35888fa2e8642b8 +size 1109721376 diff --git a/phi-2-super.i1-Q2_K_S.gguf b/phi-2-super.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b8aafa8 --- /dev/null +++ b/phi-2-super.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d616e454a93aed0924b241b25270ff1ed8e3453677ed3b1578f018aa64869786 +size 1006502176 diff --git a/phi-2-super.i1-Q3_K_L.gguf b/phi-2-super.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e56dc78 --- /dev/null +++ b/phi-2-super.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869a151a1266c54a2c13a5d9ab1133cec82b287b80712199d05a17a8dcce44fd +size 1575231776 diff --git a/phi-2-super.i1-Q3_K_M.gguf b/phi-2-super.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d0645f5 --- /dev/null +++ b/phi-2-super.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d2d0ff0bfc7d2e27ad9aae71857612d926a843770d0c818225ba23cd716eef +size 1426137376 diff --git a/phi-2-super.i1-Q3_K_S.gguf b/phi-2-super.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ccf8f75 --- /dev/null +++ b/phi-2-super.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff36c7c3208f542106df7d0fc59360844d67fae7e73a20bc70a02bc5aac4c78 +size 1250828576 diff --git a/phi-2-super.i1-Q4_0.gguf b/phi-2-super.i1-Q4_0.gguf new file mode 100644 index 0000000..3dd75e6 --- /dev/null +++ b/phi-2-super.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9c75c439c0c45cd08f91a9059e4826fd6b9bd498cc89a726dd339f86339ea4 +size 1609023776 diff --git a/phi-2-super.i1-Q4_1.gguf b/phi-2-super.i1-Q4_1.gguf new file mode 100644 index 0000000..5435f9d --- /dev/null +++ b/phi-2-super.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b556783412d5d5c93dfb8b3f36632d1f5e5070c2d9e63d7cee3ff2e14f4750 +size 1767948576 diff --git a/phi-2-super.i1-Q4_K_M.gguf b/phi-2-super.i1-Q4_K_M.gguf new file mode 100644 index 0000000..19360dd --- /dev/null +++ b/phi-2-super.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdc84b8fd494d65f1502967a7818cd47ea06389b556c44b0c6d6b4c2bd04cb3 +size 1737638176 diff --git a/phi-2-super.i1-Q4_K_S.gguf b/phi-2-super.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c500c14 --- /dev/null +++ b/phi-2-super.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3dec1cd7607e7110ebc54863ffe2a40dc1c8f93cfd2e5a97ee922cdec592825 +size 1618854176 diff --git a/phi-2-super.i1-Q5_K_M.gguf b/phi-2-super.i1-Q5_K_M.gguf new file mode 100644 index 0000000..dc509fd --- /dev/null +++ b/phi-2-super.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11531b348f0da58484c6afaeae7f8b4150b5a76116239232ab31dd0e7115893f +size 2003058976 diff --git a/phi-2-super.i1-Q5_K_S.gguf b/phi-2-super.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3b5f064 --- /dev/null +++ b/phi-2-super.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af12521f45daae860afbdf6a8edda12e0cf84130a7d84777c2df6d0b6cf24fab +size 1933426976 diff --git a/phi-2-super.i1-Q6_K.gguf b/phi-2-super.i1-Q6_K.gguf new file mode 100644 index 0000000..2e02a5f --- /dev/null +++ b/phi-2-super.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5210690c8fa7a687f7d9b691520382056274b1855f8f03b7713186773606f1 +size 2285068576