commit 772cc531b911e0f90474a0f0ca74f426472bf1e2 Author: ModelHub XC Date: Thu Jun 4 04:12:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MIST-Mini-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d489f18 --- /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 +MIST-Mini-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MIST-Mini-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MIST-Mini-8B.IQ4_XS.gguf b/MIST-Mini-8B.IQ4_XS.gguf new file mode 100644 index 0000000..65b4e6d --- /dev/null +++ b/MIST-Mini-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370d4adeb0d4afbb7891c6dd78ab4d2f574988caf152f08dfc7d373806b8fa0d +size 4484364256 diff --git a/MIST-Mini-8B.Q2_K.gguf b/MIST-Mini-8B.Q2_K.gguf new file mode 100644 index 0000000..06e31a8 --- /dev/null +++ b/MIST-Mini-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7246e33dd93f6a021c56e7876fcb032fd758aa2ffd641be398415c90dd9e540 +size 3179132896 diff --git a/MIST-Mini-8B.Q3_K_L.gguf b/MIST-Mini-8B.Q3_K_L.gguf new file mode 100644 index 0000000..139ff16 --- /dev/null +++ b/MIST-Mini-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54c356c658953a36f2a327fdb803d7022473fa128bc2983dcd4ee28a4ff5505 +size 4321957856 diff --git a/MIST-Mini-8B.Q3_K_M.gguf b/MIST-Mini-8B.Q3_K_M.gguf new file mode 100644 index 0000000..9ac0a27 --- /dev/null +++ b/MIST-Mini-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52402f2c862ef33fcb68ed99ebfdb8719d15cc8ef0aab6495ad1d595ca6c9958 +size 4018919392 diff --git a/MIST-Mini-8B.Q3_K_S.gguf b/MIST-Mini-8B.Q3_K_S.gguf new file mode 100644 index 0000000..09412b5 --- /dev/null +++ b/MIST-Mini-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d2be62bea1e4478ce612320e2997289456ce656b45c222df8b77e066b863dbb +size 3664500704 diff --git a/MIST-Mini-8B.Q4_K_M.gguf b/MIST-Mini-8B.Q4_K_M.gguf new file mode 100644 index 0000000..b072cb5 --- /dev/null +++ b/MIST-Mini-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a93238b39d64d9f98156363ff6f44591200a3dd5a5ebda8066e956fa195a97d +size 4920735712 diff --git a/MIST-Mini-8B.Q4_K_S.gguf b/MIST-Mini-8B.Q4_K_S.gguf new file mode 100644 index 0000000..a796cf7 --- /dev/null +++ b/MIST-Mini-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79c34e377d358db487f4da876c25d635a379a06bf98f6cef238bd9967364eb6 +size 4692670432 diff --git a/MIST-Mini-8B.Q5_K_M.gguf b/MIST-Mini-8B.Q5_K_M.gguf new file mode 100644 index 0000000..fba84c6 --- /dev/null +++ b/MIST-Mini-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf97a8044492f1078404989df0e4591e04cd9e95fe9af39eef9a3628c88250d +size 5732988896 diff --git a/MIST-Mini-8B.Q5_K_S.gguf b/MIST-Mini-8B.Q5_K_S.gguf new file mode 100644 index 0000000..661ab03 --- /dev/null +++ b/MIST-Mini-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9c0611ffdf853295773fb301ee37afc720b0c4a2a440f76903fc890893cffa +size 5599295456 diff --git a/MIST-Mini-8B.Q6_K.gguf b/MIST-Mini-8B.Q6_K.gguf new file mode 100644 index 0000000..da8a370 --- /dev/null +++ b/MIST-Mini-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb556314afe284848bc6960c071d33597897819e6666a71f9426f5141c4124f3 +size 6596007904 diff --git a/MIST-Mini-8B.Q8_0.gguf b/MIST-Mini-8B.Q8_0.gguf new file mode 100644 index 0000000..b90ae53 --- /dev/null +++ b/MIST-Mini-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d41de9147b46dbd494d78075d44cbfacfa56443f0f085eb5e70a1d903d5a32 +size 8540772320 diff --git a/MIST-Mini-8B.f16.gguf b/MIST-Mini-8B.f16.gguf new file mode 100644 index 0000000..702c7da --- /dev/null +++ b/MIST-Mini-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e17e534a5f171e97e849476234869e1cf8b7af3ef2f89a3ee03fb8ecf76ed9 +size 16068892640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..45ca43f --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: olaverse/MIST-Mini-8B +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- dare_ties +- llama +- llama-3.1 +- mist +--- +## About + + + + + + + + + +static quants of https://huggingface.co/olaverse/MIST-Mini-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MIST-Mini-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MIST-Mini-8B-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/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MIST-Mini-8B-GGUF/resolve/main/MIST-Mini-8B.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. + +