commit c0ffade59b9be677b700c6bb970343d5e1f32761 Author: ModelHub XC Date: Sun Jun 14 04:00:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c08a837 --- /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 +dolphin-2.9-llama3-8b-256k-ties-merge.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.f16.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b-256k-ties-merge.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..06d6afd --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: FiditeNemini/dolphin-2.9-llama3-8b-256k-ties-merge +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + +static quants of https://huggingface.co/FiditeNemini/dolphin-2.9-llama3-8b-256k-ties-merge + + +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/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-256k-ties-merge-GGUF/resolve/main/dolphin-2.9-llama3-8b-256k-ties-merge.f16.gguf) | f16 | 16.2 | 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/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_M.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_M.gguf new file mode 100644 index 0000000..f5de73b --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514c2a4f0dcd9901fc86703a23c95f92ad1cb20213801666a769635c470039ac +size 3784833824 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_S.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_S.gguf new file mode 100644 index 0000000..13601f4 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c833fe56c1af87c4f6754f290faa7d2a3db09e2598179f49ffe26fa3b49601 +size 3682335520 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_XS.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_XS.gguf new file mode 100644 index 0000000..fa8f5de --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177a3b2bf6de411f5a8fe89bda85d61286bb1c59b0f075b001b59e3e1619593b +size 3518757664 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.IQ4_XS.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ4_XS.gguf new file mode 100644 index 0000000..dbcadfc --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bebce804c2ac8d6479f34728cbb7a2f8a37db3a7e6082a79ea35acbcda362bab +size 4484374112 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q2_K.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q2_K.gguf new file mode 100644 index 0000000..2cc9921 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32bad20ad5887b62f27c983e733ccfdc2db469f1a69ec3f494388f96e34bcd3f +size 3179141088 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_L.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_L.gguf new file mode 100644 index 0000000..1299950 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a345fea312527a9c27cbb10b58068c10c41423f1be7f6864a5fca9bfac76a0b2 +size 4321966880 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_M.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_M.gguf new file mode 100644 index 0000000..9f8c7e3 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094bfb45bb4957af81bed8b58bf1b4c781b92726ef5d8a1b9d7d39e755860e1d +size 4018928416 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_S.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_S.gguf new file mode 100644 index 0000000..b690314 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2729b68c9d791e766a74a2d047926b2d56c7bbcf6e4594d11a3384cda73b5b5f +size 3664509728 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_M.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_M.gguf new file mode 100644 index 0000000..9221fff --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77de584fc089dea4ebec8ed4e7fc0a851b8e20a558cd21d56c6d850a632a1811 +size 4920745824 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_S.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_S.gguf new file mode 100644 index 0000000..2523b89 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0dfa55be8a5cabe1019f53270c8a8968599b6153ab22134e9134d3a22d03e8f +size 4692680544 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_M.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_M.gguf new file mode 100644 index 0000000..b96ad68 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e63e1637665309fc51ce3de204644049e26e1e5cce458e7aa46d45f96575be +size 5733000032 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_S.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_S.gguf new file mode 100644 index 0000000..256320d --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb7bc379eb0ae5a7fb8343bb4ccd19e6a1448dda2dc0c7de6484e88ee97a625 +size 5599306592 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q6_K.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q6_K.gguf new file mode 100644 index 0000000..da0734f --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e11e32c7d5b149fe6a8f984bab1cc3dbdac41eac33d1933b2c625cec37499f +size 6596020128 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.Q8_0.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.Q8_0.gguf new file mode 100644 index 0000000..b702a30 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29834a328fc1d9607de3cc482007785e830bb52e6583046c339741078afbe3e +size 8540788512 diff --git a/dolphin-2.9-llama3-8b-256k-ties-merge.f16.gguf b/dolphin-2.9-llama3-8b-256k-ties-merge.f16.gguf new file mode 100644 index 0000000..4ef2a11 --- /dev/null +++ b/dolphin-2.9-llama3-8b-256k-ties-merge.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e636481e7f43091dc478a26cba4ba82c8eeb265ed918ab3cd0177666c3976ebf +size 16068924192