commit 1d5f0d9f3aec31a7e87ed93e04d5ece5433ee401 Author: ModelHub XC Date: Mon Oct 12 15:27:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a80c15 --- /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 +Phi-3-mini-4k-instruct-dpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-4k-instruct-dpo.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-3-mini-4k-instruct-dpo.IQ4_XS.gguf b/Phi-3-mini-4k-instruct-dpo.IQ4_XS.gguf new file mode 100644 index 0000000..cb88164 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b7066172cf7aded858c8f2d58d6c96fddace48a54928f18e493fa3eb97ac16 +size 2075581280 diff --git a/Phi-3-mini-4k-instruct-dpo.Q2_K.gguf b/Phi-3-mini-4k-instruct-dpo.Q2_K.gguf new file mode 100644 index 0000000..810876c --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1acf098a12fc5250b4cb1163103d0387b071401fec94276acec588717e83d2c +size 1416204128 diff --git a/Phi-3-mini-4k-instruct-dpo.Q3_K_L.gguf b/Phi-3-mini-4k-instruct-dpo.Q3_K_L.gguf new file mode 100644 index 0000000..93d9b44 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b2072692a8fda9804db905f08bddc549831267ede89aa3f3619ddbd4bda07e +size 2087597408 diff --git a/Phi-3-mini-4k-instruct-dpo.Q3_K_M.gguf b/Phi-3-mini-4k-instruct-dpo.Q3_K_M.gguf new file mode 100644 index 0000000..cea4b85 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba84fbab7441a69ae4234a0e40aab5d856db35fbbec44a17a5bd1060f4752f8 +size 1955476832 diff --git a/Phi-3-mini-4k-instruct-dpo.Q3_K_S.gguf b/Phi-3-mini-4k-instruct-dpo.Q3_K_S.gguf new file mode 100644 index 0000000..6ceae7c --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f53d3b5f4469a5b690138dc629b905e23fb2467ba5d4441714d3fc43323c110 +size 1681798496 diff --git a/Phi-3-mini-4k-instruct-dpo.Q4_K_M.gguf b/Phi-3-mini-4k-instruct-dpo.Q4_K_M.gguf new file mode 100644 index 0000000..939a792 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9abad281b9105497be98ef3588694c6014bc7c27cbfd096b114b147157f9c14c +size 2393232224 diff --git a/Phi-3-mini-4k-instruct-dpo.Q4_K_S.gguf b/Phi-3-mini-4k-instruct-dpo.Q4_K_S.gguf new file mode 100644 index 0000000..5623704 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ae3c40f4c5f1ad2faf83073ca66f423248cf4cfa0b595c80c6bc807949e9b5 +size 2188759904 diff --git a/Phi-3-mini-4k-instruct-dpo.Q5_K_M.gguf b/Phi-3-mini-4k-instruct-dpo.Q5_K_M.gguf new file mode 100644 index 0000000..9ff4693 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6799a9c4f980c9d2fd73c58f3c278c0dfceb6cda6dc3df137378d09a5fcdb22 +size 2815275872 diff --git a/Phi-3-mini-4k-instruct-dpo.Q5_K_S.gguf b/Phi-3-mini-4k-instruct-dpo.Q5_K_S.gguf new file mode 100644 index 0000000..fcc5708 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250c1259be16cd80e48c20955d4d49941c6488ac956b0aedcdb5c7ed042466a0 +size 2641474400 diff --git a/Phi-3-mini-4k-instruct-dpo.Q6_K.gguf b/Phi-3-mini-4k-instruct-dpo.Q6_K.gguf new file mode 100644 index 0000000..a1a1440 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caded033a4592180d64efca23b594c1a75a6dcdaa0d1eae3b9a6b19a61c7a4ae +size 3135852896 diff --git a/Phi-3-mini-4k-instruct-dpo.Q8_0.gguf b/Phi-3-mini-4k-instruct-dpo.Q8_0.gguf new file mode 100644 index 0000000..82e1832 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12df110425ace73b8acac3a572b03ccaf2bf56001603d6dd1e008e4633a8830 +size 4061222240 diff --git a/Phi-3-mini-4k-instruct-dpo.f16.gguf b/Phi-3-mini-4k-instruct-dpo.f16.gguf new file mode 100644 index 0000000..a13c8b9 --- /dev/null +++ b/Phi-3-mini-4k-instruct-dpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1508ff4c7bb3bd0c942a9af6b05369e0a9eac0d986e82ba40cb9c11ff7aac77c +size 7643297120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..435c082 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ryota39/Phi-3-mini-4k-instruct-dpo +datasets: +- llm-jp/hh-rlhf-12k-ja +language: +- ja +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/ryota39/Phi-3-mini-4k-instruct-dpo + + +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/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-3-mini-4k-instruct-dpo-GGUF/resolve/main/Phi-3-mini-4k-instruct-dpo.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. 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. + +