commit 8fc7c6818c4ae7c0a39af025224a97ac95ddf706 Author: ModelHub XC Date: Sat Jun 27 05:42:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyDolphin-3x-MoE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c1f952 --- /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 +TinyDolphin-3x-MoE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-3x-MoE.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d1aa69a --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: jtatman/TinyDolphin-3x-MoE +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- frankenmoe +- merge +- mergekit +- lazymergekit +- cognitivecomputations/TinyDolphin-2.8.1-1.1b +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jtatman/TinyDolphin-3x-MoE + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyDolphin-3x-MoE-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-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/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q4_K_S.gguf) | Q4_K_S | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-3x-MoE-GGUF/resolve/main/TinyDolphin-3x-MoE.f16.gguf) | f16 | 5.3 | 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/TinyDolphin-3x-MoE.IQ4_XS.gguf b/TinyDolphin-3x-MoE.IQ4_XS.gguf new file mode 100644 index 0000000..014c71a --- /dev/null +++ b/TinyDolphin-3x-MoE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5caa60845c8d726b71f79c13bf1256a624c535f98d28cf0b4d8153b70a033eda +size 1426411680 diff --git a/TinyDolphin-3x-MoE.Q2_K.gguf b/TinyDolphin-3x-MoE.Q2_K.gguf new file mode 100644 index 0000000..99d095f --- /dev/null +++ b/TinyDolphin-3x-MoE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c239e03b527260207ef0287816c3cd501b51c33f37925e1a4cb7af025412848 +size 983805280 diff --git a/TinyDolphin-3x-MoE.Q3_K_L.gguf b/TinyDolphin-3x-MoE.Q3_K_L.gguf new file mode 100644 index 0000000..4098387 --- /dev/null +++ b/TinyDolphin-3x-MoE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c463928b186f6cf84ed190233093da042a27016c56630188f24dc4f34cce2c7c +size 1377132288 diff --git a/TinyDolphin-3x-MoE.Q3_K_M.gguf b/TinyDolphin-3x-MoE.Q3_K_M.gguf new file mode 100644 index 0000000..6b11b63 --- /dev/null +++ b/TinyDolphin-3x-MoE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2921e2bad21e8da915e9603a5c6855fc397347d2f17d1f9d76940ef4082486 +size 1273454336 diff --git a/TinyDolphin-3x-MoE.Q3_K_S.gguf b/TinyDolphin-3x-MoE.Q3_K_S.gguf new file mode 100644 index 0000000..3cc48e4 --- /dev/null +++ b/TinyDolphin-3x-MoE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0b4ebdcbe4e80bff6d08cdc4394724e29cccc651650516a49cbf33d2693e70 +size 1154105088 diff --git a/TinyDolphin-3x-MoE.Q4_K_M.gguf b/TinyDolphin-3x-MoE.Q4_K_M.gguf new file mode 100644 index 0000000..c5cafce --- /dev/null +++ b/TinyDolphin-3x-MoE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65ea5b49b695ec21cb31a21d7aafa338c075b3538e62347d0556b26f4f0c565 +size 1584263456 diff --git a/TinyDolphin-3x-MoE.Q4_K_S.gguf b/TinyDolphin-3x-MoE.Q4_K_S.gguf new file mode 100644 index 0000000..02be5d8 --- /dev/null +++ b/TinyDolphin-3x-MoE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c5668d808ec4e9ee1bc2bd3f5fad8be1d818f7e02a06070b1c7a701eb265de7 +size 1502613792 diff --git a/TinyDolphin-3x-MoE.Q5_K_M.gguf b/TinyDolphin-3x-MoE.Q5_K_M.gguf new file mode 100644 index 0000000..ad87be5 --- /dev/null +++ b/TinyDolphin-3x-MoE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a01fc4dfb5c1f90f614cd7a3b2657e8cb399e57cc3e0c2050e3939c94c52c61d +size 1859973920 diff --git a/TinyDolphin-3x-MoE.Q5_K_S.gguf b/TinyDolphin-3x-MoE.Q5_K_S.gguf new file mode 100644 index 0000000..4a1ed45 --- /dev/null +++ b/TinyDolphin-3x-MoE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c46884a7cbe0c7b9815be3be97f84e6f92e9e9cfbb1d015d83da0e71a77929 +size 1813320480 diff --git a/TinyDolphin-3x-MoE.Q6_K.gguf b/TinyDolphin-3x-MoE.Q6_K.gguf new file mode 100644 index 0000000..6bc201c --- /dev/null +++ b/TinyDolphin-3x-MoE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b530fc26fb4217e129eea3a0aa4e39ed08fcb2b80097fdbbe9e570046ae52540 +size 2152916288 diff --git a/TinyDolphin-3x-MoE.Q8_0.gguf b/TinyDolphin-3x-MoE.Q8_0.gguf new file mode 100644 index 0000000..b58a3eb --- /dev/null +++ b/TinyDolphin-3x-MoE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2786037ca0c07693aab85dda5414cfd9fe90ae8e69bc77a85b0c1a6bdb93d418 +size 2788052224 diff --git a/TinyDolphin-3x-MoE.f16.gguf b/TinyDolphin-3x-MoE.f16.gguf new file mode 100644 index 0000000..28155a3 --- /dev/null +++ b/TinyDolphin-3x-MoE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f659ccacbda83b2710e40acb60af5bfb9f723ad0d2371e5d1b3bf4aa977a11ce +size 5246642944