commit 7ead60d6ee602c844246908283729295470a21af Author: ModelHub XC Date: Sun Oct 11 07:21:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyDolphin-2.8-1.1b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c5fe9ef --- /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-2.8-1.1b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyDolphin-2.8-1.1b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f7a75f4 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: QuixiAI/TinyDolphin-2.8-1.1b +datasets: +- cerebras/SlimPajama-627B +- bigcode/starcoderdata +- teknium/openhermes +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/QuixiAI/TinyDolphin-2.8-1.1b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyDolphin-2.8-1.1b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-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-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyDolphin-2.8-1.1b-GGUF/resolve/main/TinyDolphin-2.8-1.1b.f16.gguf) | f16 | 2.3 | 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. 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. + + diff --git a/TinyDolphin-2.8-1.1b.IQ4_XS.gguf b/TinyDolphin-2.8-1.1b.IQ4_XS.gguf new file mode 100644 index 0000000..fe2ea73 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe699171163339622569069226d6441a4e6d9f3b918838a685793017c40cf4f +size 609813984 diff --git a/TinyDolphin-2.8-1.1b.Q2_K.gguf b/TinyDolphin-2.8-1.1b.Q2_K.gguf new file mode 100644 index 0000000..3bd39fd --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074440b9ed46ad64069718ec7bf4fdd94e7a3c7aaca68db8dc2d5bad43db82d7 +size 432136864 diff --git a/TinyDolphin-2.8-1.1b.Q3_K_L.gguf b/TinyDolphin-2.8-1.1b.Q3_K_L.gguf new file mode 100644 index 0000000..3531c97 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c9c3f5967774315048d20da5a9b6ba5785cc369fb35afdf56dc40089477c5e +size 591533120 diff --git a/TinyDolphin-2.8-1.1b.Q3_K_M.gguf b/TinyDolphin-2.8-1.1b.Q3_K_M.gguf new file mode 100644 index 0000000..4cb7a6f --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d470156a7034fab7bf19e1c453cc0b3db5a2ca4454a53f6660c45d5b35792dd +size 548410432 diff --git a/TinyDolphin-2.8-1.1b.Q3_K_S.gguf b/TinyDolphin-2.8-1.1b.Q3_K_S.gguf new file mode 100644 index 0000000..c8cd12f --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f4f55f6585baffc7c63a1800d4c18a8f3374d0d0f17bc198d6431faf5ceb5d +size 499348544 diff --git a/TinyDolphin-2.8-1.1b.Q4_K_M.gguf b/TinyDolphin-2.8-1.1b.Q4_K_M.gguf new file mode 100644 index 0000000..a486372 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0585f94f5e856e9f3a983d439866821a6b216eead0c2f9901c1718ffbd0d884b +size 667821664 diff --git a/TinyDolphin-2.8-1.1b.Q4_K_S.gguf b/TinyDolphin-2.8-1.1b.Q4_K_S.gguf new file mode 100644 index 0000000..8f19ff8 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d84fd48401d60dcb0d28e7b83582310cff76c51f22ec9758ae250dd036d417 +size 639878752 diff --git a/TinyDolphin-2.8-1.1b.Q5_K_M.gguf b/TinyDolphin-2.8-1.1b.Q5_K_M.gguf new file mode 100644 index 0000000..da6b9e9 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf270470c9e0a796faac7634bc493b113b8c5984f71020305c0c3d1fe5518de +size 782051424 diff --git a/TinyDolphin-2.8-1.1b.Q5_K_S.gguf b/TinyDolphin-2.8-1.1b.Q5_K_S.gguf new file mode 100644 index 0000000..9ec8ff7 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5673baf9c8cfee7cd12d05853275b3002e408d3c5cea99988da0c59ca0aa774a +size 766036064 diff --git a/TinyDolphin-2.8-1.1b.Q6_K.gguf b/TinyDolphin-2.8-1.1b.Q6_K.gguf new file mode 100644 index 0000000..ca95712 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa04bd1cd170b486c37c07fe98610a5617391c84bae2f0a48ec4f97a07b36f46 +size 903420544 diff --git a/TinyDolphin-2.8-1.1b.Q8_0.gguf b/TinyDolphin-2.8-1.1b.Q8_0.gguf new file mode 100644 index 0000000..0f717a2 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4277eede843ad9da7ad9730b1c9e1edef3677ad59584cc4dc62fdaf8ba7c35f5 +size 1169818176 diff --git a/TinyDolphin-2.8-1.1b.f16.gguf b/TinyDolphin-2.8-1.1b.f16.gguf new file mode 100644 index 0000000..1600935 --- /dev/null +++ b/TinyDolphin-2.8-1.1b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87ff23fe5fcd9201a3910710117c48e192bae9eedb23f8e4270e8daf2c6f0b9 +size 2201034816