From 79ff5ff4acf7973427fd1014cb47afe3e5f78f02 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 2 Oct 2026 05:33:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/martinLLM-phi-4b-128k-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++++ README.md | 64 +++++++++++++++++++++++++++++++ martinLLM-phi-4b-128k.IQ4_XS.gguf | 3 ++ martinLLM-phi-4b-128k.Q2_K.gguf | 3 ++ martinLLM-phi-4b-128k.Q3_K_L.gguf | 3 ++ martinLLM-phi-4b-128k.Q3_K_M.gguf | 3 ++ martinLLM-phi-4b-128k.Q3_K_S.gguf | 3 ++ martinLLM-phi-4b-128k.Q4_K_M.gguf | 3 ++ martinLLM-phi-4b-128k.Q4_K_S.gguf | 3 ++ martinLLM-phi-4b-128k.Q5_K_M.gguf | 3 ++ martinLLM-phi-4b-128k.Q5_K_S.gguf | 3 ++ martinLLM-phi-4b-128k.Q6_K.gguf | 3 ++ martinLLM-phi-4b-128k.Q8_0.gguf | 3 ++ martinLLM-phi-4b-128k.f16.gguf | 3 ++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 martinLLM-phi-4b-128k.IQ4_XS.gguf create mode 100644 martinLLM-phi-4b-128k.Q2_K.gguf create mode 100644 martinLLM-phi-4b-128k.Q3_K_L.gguf create mode 100644 martinLLM-phi-4b-128k.Q3_K_M.gguf create mode 100644 martinLLM-phi-4b-128k.Q3_K_S.gguf create mode 100644 martinLLM-phi-4b-128k.Q4_K_M.gguf create mode 100644 martinLLM-phi-4b-128k.Q4_K_S.gguf create mode 100644 martinLLM-phi-4b-128k.Q5_K_M.gguf create mode 100644 martinLLM-phi-4b-128k.Q5_K_S.gguf create mode 100644 martinLLM-phi-4b-128k.Q6_K.gguf create mode 100644 martinLLM-phi-4b-128k.Q8_0.gguf create mode 100644 martinLLM-phi-4b-128k.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33a9039 --- /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 +martinLLM-phi-4b-128k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.f16.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +martinLLM-phi-4b-128k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..037d51b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: fbeawels/martinLLM-phi-4b-128k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/fbeawels/martinLLM-phi-4b-128k + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/martinLLM-phi-4b-128k-GGUF/resolve/main/martinLLM-phi-4b-128k.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/martinLLM-phi-4b-128k.IQ4_XS.gguf b/martinLLM-phi-4b-128k.IQ4_XS.gguf new file mode 100644 index 0000000..4fb1a43 --- /dev/null +++ b/martinLLM-phi-4b-128k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b670168f38a79ab3cc4013ace09b44ce37037ec2054007d6130f0ddbfc1c42 +size 2075581568 diff --git a/martinLLM-phi-4b-128k.Q2_K.gguf b/martinLLM-phi-4b-128k.Q2_K.gguf new file mode 100644 index 0000000..b0e358b --- /dev/null +++ b/martinLLM-phi-4b-128k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e2f9393986bd5287b3fe8bb2c5ee1f71f26fecbb823d1997b28a8a24902319 +size 1416204416 diff --git a/martinLLM-phi-4b-128k.Q3_K_L.gguf b/martinLLM-phi-4b-128k.Q3_K_L.gguf new file mode 100644 index 0000000..98773ec --- /dev/null +++ b/martinLLM-phi-4b-128k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1eadcfbcc74ccb18ca66c73d94400defc1f22018db3c2328cf6f78496d4f490 +size 2087597696 diff --git a/martinLLM-phi-4b-128k.Q3_K_M.gguf b/martinLLM-phi-4b-128k.Q3_K_M.gguf new file mode 100644 index 0000000..0e5f50b --- /dev/null +++ b/martinLLM-phi-4b-128k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda575ded740d05e2232e2e2413b5d94fd178111bcf98a346a8f56be9bf24daf +size 1955477120 diff --git a/martinLLM-phi-4b-128k.Q3_K_S.gguf b/martinLLM-phi-4b-128k.Q3_K_S.gguf new file mode 100644 index 0000000..7752dca --- /dev/null +++ b/martinLLM-phi-4b-128k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c19d3d3023d3ca8994d04ca09c440d0e944b39786fb63a67d18afa03d6f9bc1 +size 1681798784 diff --git a/martinLLM-phi-4b-128k.Q4_K_M.gguf b/martinLLM-phi-4b-128k.Q4_K_M.gguf new file mode 100644 index 0000000..d3f7938 --- /dev/null +++ b/martinLLM-phi-4b-128k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06608e4105c61d8870cd06bed1d0b9390afef41ece6bfffc687ff3416771f2e +size 2393232512 diff --git a/martinLLM-phi-4b-128k.Q4_K_S.gguf b/martinLLM-phi-4b-128k.Q4_K_S.gguf new file mode 100644 index 0000000..a249711 --- /dev/null +++ b/martinLLM-phi-4b-128k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88fe38d7a11a91f3d182d838bf575140add4611415f17c1d93498c5e2588d6d7 +size 2188760192 diff --git a/martinLLM-phi-4b-128k.Q5_K_M.gguf b/martinLLM-phi-4b-128k.Q5_K_M.gguf new file mode 100644 index 0000000..cffefeb --- /dev/null +++ b/martinLLM-phi-4b-128k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cff285d20ea476183b07a655868297bc3eca38954e63542fa14de84909baa8a +size 2815276160 diff --git a/martinLLM-phi-4b-128k.Q5_K_S.gguf b/martinLLM-phi-4b-128k.Q5_K_S.gguf new file mode 100644 index 0000000..232f077 --- /dev/null +++ b/martinLLM-phi-4b-128k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9337b5736eef881587eaaf3abf392a725ab536f7b8f45fb6abb98670f153a0 +size 2641474688 diff --git a/martinLLM-phi-4b-128k.Q6_K.gguf b/martinLLM-phi-4b-128k.Q6_K.gguf new file mode 100644 index 0000000..520cfc9 --- /dev/null +++ b/martinLLM-phi-4b-128k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95614f5fe64e814547a56ccad73e0a89e29fcae69ebf57f7d6fed822726a472e +size 3135853184 diff --git a/martinLLM-phi-4b-128k.Q8_0.gguf b/martinLLM-phi-4b-128k.Q8_0.gguf new file mode 100644 index 0000000..3cbf616 --- /dev/null +++ b/martinLLM-phi-4b-128k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e599d546fd6a5ea8044625c179b0c88c325aca9a791179226d22c9a8837b23 +size 4061222528 diff --git a/martinLLM-phi-4b-128k.f16.gguf b/martinLLM-phi-4b-128k.f16.gguf new file mode 100644 index 0000000..e6a9f0d --- /dev/null +++ b/martinLLM-phi-4b-128k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc4310ad57210ae9453e74da9f9c11d5784a6bf8e579da589d5c8f852b5d9e9 +size 7643297408