commit 5aa84185ea6487b70811438134e780903672a396 Author: ModelHub XC Date: Tue Aug 18 08:13:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b68377 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Qwen2-2B-Dolphin-RepleteCoder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-2B-Dolphin-RepleteCoder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-2B-Dolphin-RepleteCoder.IQ3_M.gguf b/Qwen2-2B-Dolphin-RepleteCoder.IQ3_M.gguf new file mode 100644 index 0000000..46cf61d --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548b8517cf262d810c1906711083e6e771f86a1f44220b2c742f7c313bfb6eae +size 1042711808 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.IQ3_S.gguf b/Qwen2-2B-Dolphin-RepleteCoder.IQ3_S.gguf new file mode 100644 index 0000000..a06169f --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324e9fe1ad236434840dc8f55e22bbfd0e0cf63a63dd4e909944e7ea298efc17 +size 1024120064 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.IQ3_XS.gguf b/Qwen2-2B-Dolphin-RepleteCoder.IQ3_XS.gguf new file mode 100644 index 0000000..1e339a2 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd59233a0492bb32c41404057a0ee522519ca7f19f43998d2a25df30bbb68f67 +size 984638720 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.IQ4_XS.gguf b/Qwen2-2B-Dolphin-RepleteCoder.IQ4_XS.gguf new file mode 100644 index 0000000..9c24fbb --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99165fbd2f44122f4d374d86fd023edd9183d1e29e43fa13721e8fab895d0d11 +size 1227841280 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q2_K.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q2_K.gguf new file mode 100644 index 0000000..60bafce --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1fb80311c35ec92786ce6b39b3b8dfb3bdbf68505123f4454a7f14b3078770 +size 889715456 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_L.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_L.gguf new file mode 100644 index 0000000..432cab2 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09504f4cb32eca71869544ab7976354d0e2030e81a155ca6f71fdc4e3a10e6b6 +size 1175520512 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_M.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_M.gguf new file mode 100644 index 0000000..3d48521 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f286784069744de360b75900cd7c0a5ed960063c044ee0ea978b1f1f3504b91 +size 1104741632 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_S.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_S.gguf new file mode 100644 index 0000000..432487b --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aae731244a06f64bbe620c108b20b6e7d4b5e0dded1252a8c85249a7ea3a504 +size 1022240000 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_M.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_M.gguf new file mode 100644 index 0000000..72bbe29 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5865ca36f57f233133cd2f46ee9abdc45a086f2ba215e36374dc77a05555c7 +size 1342654208 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_S.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_S.gguf new file mode 100644 index 0000000..93dd6f1 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f4c1b33868c8def611e7fc2dfcf95ae87bdae92d13fcf7a94add4e9936815f8 +size 1284040448 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_M.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_M.gguf new file mode 100644 index 0000000..163c135 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f186df85bf0e8259d54c9d1d595b74ee4bfa675cb6029e3715dc79e4b8c90f4f +size 1550542592 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_S.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_S.gguf new file mode 100644 index 0000000..48d159c --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd0e2d5176475b592645c3ab53164cb37dafa1418b2a9c7eb3433a115a92e26 +size 1516701440 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q6_K.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q6_K.gguf new file mode 100644 index 0000000..0eef16c --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a34123beb61dfe9ed0d4311785c00f6025263d153ec42ebe32ea71fe62c58bf8 +size 1771424000 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.Q8_0.gguf b/Qwen2-2B-Dolphin-RepleteCoder.Q8_0.gguf new file mode 100644 index 0000000..b208d5e --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf089e601a9f94a59947c7a1f4aa1d31749f7872836e36df0ee5adaa89cb1e6 +size 2292438272 diff --git a/Qwen2-2B-Dolphin-RepleteCoder.f16.gguf b/Qwen2-2B-Dolphin-RepleteCoder.f16.gguf new file mode 100644 index 0000000..4f21045 --- /dev/null +++ b/Qwen2-2B-Dolphin-RepleteCoder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9ca708162a2ab6db6b38fe530c0cc18f5dfd2bea11b38fab4587f5057ae7ae +size 4309267712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c8987c7 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: mergekit-community/Qwen2-2B-Dolphin-RepleteCoder +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/Qwen2-2B-Dolphin-RepleteCoder + + +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/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.IQ3_XS.gguf) | IQ3_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.IQ3_S.gguf) | IQ3_S | 1.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.IQ3_M.gguf) | IQ3_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_M.gguf) | Q3_K_M | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q3_K_L.gguf) | Q3_K_L | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.IQ4_XS.gguf) | IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_S.gguf) | Q4_K_S | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q4_K_M.gguf) | Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_S.gguf) | Q5_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q5_K_M.gguf) | Q5_K_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q6_K.gguf) | Q6_K | 1.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.Q8_0.gguf) | Q8_0 | 2.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-2B-Dolphin-RepleteCoder-GGUF/resolve/main/Qwen2-2B-Dolphin-RepleteCoder.f16.gguf) | f16 | 4.4 | 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. + +