commit 56eaa6ce2fb9cc6523e4ad19ffe1b4b379a498e5 Author: ModelHub XC Date: Mon May 4 03:05:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi4.Turn.R1Distill.16bit-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8ba3c3b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Phi4.Turn.R1Distill.16bit.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi4.Turn.R1Distill.16bit.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi4.Turn.R1Distill.16bit.IQ4_XS.gguf b/Phi4.Turn.R1Distill.16bit.IQ4_XS.gguf new file mode 100644 index 0000000..0b1002a --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30bbd2835ffb2de8d675d7b33543d50ddef5cc5f239e939ed61bf52fb6e2d85 +size 8054026464 diff --git a/Phi4.Turn.R1Distill.16bit.Q2_K.gguf b/Phi4.Turn.R1Distill.16bit.Q2_K.gguf new file mode 100644 index 0000000..ee443c7 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d25d018249e526db17942045c8435812c493bd622e1e4187599f783ae27a2e4 +size 5608796384 diff --git a/Phi4.Turn.R1Distill.16bit.Q3_K_L.gguf b/Phi4.Turn.R1Distill.16bit.Q3_K_L.gguf new file mode 100644 index 0000000..050d632 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15080bc73656ffca3a9d9f9756d53e05ebc37666fa05beff5c24644e63ae57fa +size 7788851424 diff --git a/Phi4.Turn.R1Distill.16bit.Q3_K_M.gguf b/Phi4.Turn.R1Distill.16bit.Q3_K_M.gguf new file mode 100644 index 0000000..4a21d5a --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b519e00957b111b9f47cc82bf16cedccaf2d6cfa76648528cf2ec19c12b467db +size 7190835424 diff --git a/Phi4.Turn.R1Distill.16bit.Q3_K_S.gguf b/Phi4.Turn.R1Distill.16bit.Q3_K_S.gguf new file mode 100644 index 0000000..cb1fe6d --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9e848282bcbccb92e0c788496b5cfba2a06a5f250a1123c65d894696a340c5 +size 6504755424 diff --git a/Phi4.Turn.R1Distill.16bit.Q4_K_M.gguf b/Phi4.Turn.R1Distill.16bit.Q4_K_M.gguf new file mode 100644 index 0000000..62f3963 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46eb6959d3f50fd421c2e6265ceef91bb732e8dbe3ff704b44316874117c1797 +size 8890306784 diff --git a/Phi4.Turn.R1Distill.16bit.Q4_K_S.gguf b/Phi4.Turn.R1Distill.16bit.Q4_K_S.gguf new file mode 100644 index 0000000..a211b02 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9ecd4cc6085f487dde298a43d0de4e684e8335b8c9c31ed53070efecdb714f +size 8444047584 diff --git a/Phi4.Turn.R1Distill.16bit.Q5_K_M.gguf b/Phi4.Turn.R1Distill.16bit.Q5_K_M.gguf new file mode 100644 index 0000000..367881e --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:accb7a92f6036534da324430b67c297f56e84e63c88a6333f43df3e2d43449e1 +size 10412708064 diff --git a/Phi4.Turn.R1Distill.16bit.Q5_K_S.gguf b/Phi4.Turn.R1Distill.16bit.Q5_K_S.gguf new file mode 100644 index 0000000..94106e6 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401d6bf6a1224de4d7e1e05547e84cc8885e931f47df135a4739f79482e393c2 +size 10151588064 diff --git a/Phi4.Turn.R1Distill.16bit.Q6_K.gguf b/Phi4.Turn.R1Distill.16bit.Q6_K.gguf new file mode 100644 index 0000000..c27ca92 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:893a643543a0499e4fdb399d7ab5bf92af164990cfc376964653bf32f0eaf7bf +size 12030259424 diff --git a/Phi4.Turn.R1Distill.16bit.Q8_0.gguf b/Phi4.Turn.R1Distill.16bit.Q8_0.gguf new file mode 100644 index 0000000..0628b83 --- /dev/null +++ b/Phi4.Turn.R1Distill.16bit.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7c24c92b3c2afad01c5b5b40fa68cf018739e8ad96a8325908906214270984 +size 15580508384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..77e1ac2 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Quazim0t0/Phi4.Turn.R1Distill-v1.0-Tensors +datasets: +- bespokelabs/Bespoke-Stratos-17k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Quazim0t0/Phi4.Turn.R1Distill-v1.0-Tensors + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-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/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q2_K.gguf) | Q2_K | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q3_K_S.gguf) | Q3_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q3_K_M.gguf) | Q3_K_M | 7.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q3_K_L.gguf) | Q3_K_L | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.IQ4_XS.gguf) | IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q4_K_S.gguf) | Q4_K_S | 8.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q4_K_M.gguf) | Q4_K_M | 9.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q5_K_S.gguf) | Q5_K_S | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q5_K_M.gguf) | Q5_K_M | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q6_K.gguf) | Q6_K | 12.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi4.Turn.R1Distill.16bit-GGUF/resolve/main/Phi4.Turn.R1Distill.16bit.Q8_0.gguf) | Q8_0 | 15.7 | fast, best quality | + +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. + +