commit 78a6292bb03729b73d33e6e894ca768a8a443e02 Author: ModelHub XC Date: Mon Jun 1 09:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi3-ITA-mini-4K-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..576f8a4 --- /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 +Phi3-ITA-mini-4K-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi3-ITA-mini-4K-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi3-ITA-mini-4K-instruct.IQ4_XS.gguf b/Phi3-ITA-mini-4K-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..3c4b71b --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f93c9c5c37cf8c35144a0c10828f71af6f48e74e9deaa387b3d0cc81ff3f64 +size 2075581536 diff --git a/Phi3-ITA-mini-4K-instruct.Q2_K.gguf b/Phi3-ITA-mini-4K-instruct.Q2_K.gguf new file mode 100644 index 0000000..a9155ce --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec3e444a7e0380d97b262d9d14c30f798f50179bf3cca2ae79eaeef6a17734d +size 1416204384 diff --git a/Phi3-ITA-mini-4K-instruct.Q3_K_L.gguf b/Phi3-ITA-mini-4K-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..fd2558a --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a219bc97b2401d30c2fe666a44182d9537808ef33fc08fe0cfabd87b4f520418 +size 2087597664 diff --git a/Phi3-ITA-mini-4K-instruct.Q3_K_M.gguf b/Phi3-ITA-mini-4K-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..15a6e12 --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a78995477fd91e7ebb7fb81b7b5bf2ecbd01cddaab3c24434746a69bdfc2de9 +size 1955477088 diff --git a/Phi3-ITA-mini-4K-instruct.Q3_K_S.gguf b/Phi3-ITA-mini-4K-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bdfa3aa --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7df319aea5924ab9f75d6e4a947987c547a885499e35dbbe981156883863fe2 +size 1681798752 diff --git a/Phi3-ITA-mini-4K-instruct.Q4_K_M.gguf b/Phi3-ITA-mini-4K-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..3a449c2 --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3debf3b291e16885e09ba2e8d3c546022e3803c5eb02e913a2e52c8b99ce0f +size 2393232480 diff --git a/Phi3-ITA-mini-4K-instruct.Q4_K_S.gguf b/Phi3-ITA-mini-4K-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..24129a8 --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdb63d8056b1840ee80b502e8d6a4d6a0fa740f43cfcb424ae76d4c4894655f +size 2188760160 diff --git a/Phi3-ITA-mini-4K-instruct.Q5_K_M.gguf b/Phi3-ITA-mini-4K-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..cd7900f --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ebea8c86a3c2ade780ec0e5be2bbb971d9929a3626c86e27bf694a6770de04 +size 2815276128 diff --git a/Phi3-ITA-mini-4K-instruct.Q5_K_S.gguf b/Phi3-ITA-mini-4K-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..846cc2f --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c99308983cd01fb7192c5bf048890fa2d9cedc7a8c38331fca7b13038cc637d +size 2641474656 diff --git a/Phi3-ITA-mini-4K-instruct.Q6_K.gguf b/Phi3-ITA-mini-4K-instruct.Q6_K.gguf new file mode 100644 index 0000000..a22cc38 --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5d483e72aa0aab85c50ff80ded2d5ded2f2a0c8318c4199d6385eab37ec374 +size 3135853152 diff --git a/Phi3-ITA-mini-4K-instruct.Q8_0.gguf b/Phi3-ITA-mini-4K-instruct.Q8_0.gguf new file mode 100644 index 0000000..030e787 --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725b5badc0a709ef8dacbac9c2d17aa4aa40b06cb20ee47061fefc2c2d49d03e +size 4061222496 diff --git a/Phi3-ITA-mini-4K-instruct.f16.gguf b/Phi3-ITA-mini-4K-instruct.f16.gguf new file mode 100644 index 0000000..5e88d4b --- /dev/null +++ b/Phi3-ITA-mini-4K-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:553edd5a79ce7499648360f68a78d1f23dc4236cde12e6f046691edc87f70125 +size 7643297376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a75226a --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: e-palmisano/Phi3-ITA-mini-4K-instruct +language: +- it +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- trl +- sft +- phi-3 +- phi-3-mini +- italian +--- +## About + + + + + + +static quants of https://huggingface.co/e-palmisano/Phi3-ITA-mini-4K-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Phi3-ITA-mini-4K-instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-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/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-instruct.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi3-ITA-mini-4K-instruct-GGUF/resolve/main/Phi3-ITA-mini-4K-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. + +