commit 01b1b5cb6edf63b0913d894520c05c09b9be7122 Author: ModelHub XC Date: Sun Apr 12 16:13:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Vellum-3B-Ministral-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b41d7fd --- /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 +Vellum-3B-Ministral.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Vellum-3B-Ministral.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..77b3d0d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: blascotobasco/Vellum-3B-Ministral +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/blascotobasco/Vellum-3B-Ministral + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Vellum-3B-Ministral-GGUF).*** + +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/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q3_K_S.gguf) | Q3_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q5_K_S.gguf) | Q5_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Vellum-3B-Ministral-GGUF/resolve/main/Vellum-3B-Ministral.f16.gguf) | f16 | 7.8 | 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/Vellum-3B-Ministral.IQ4_XS.gguf b/Vellum-3B-Ministral.IQ4_XS.gguf new file mode 100644 index 0000000..3f2adb2 --- /dev/null +++ b/Vellum-3B-Ministral.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527cb9f32544066226dcb19d7f41357086db61f453c5dd543930da347a8324b6 +size 2186451296 diff --git a/Vellum-3B-Ministral.Q2_K.gguf b/Vellum-3B-Ministral.Q2_K.gguf new file mode 100644 index 0000000..7161a9b --- /dev/null +++ b/Vellum-3B-Ministral.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8efc3646ae721b018817dc06c547eaad99f20b1e62b028dc74c66b90445111c0 +size 1591073120 diff --git a/Vellum-3B-Ministral.Q3_K_L.gguf b/Vellum-3B-Ministral.Q3_K_L.gguf new file mode 100644 index 0000000..720eeb4 --- /dev/null +++ b/Vellum-3B-Ministral.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469328861527bc38e0f1360c680feb2688f2d091c52d348595be0c56c3243df1 +size 2107365728 diff --git a/Vellum-3B-Ministral.Q3_K_M.gguf b/Vellum-3B-Ministral.Q3_K_M.gguf new file mode 100644 index 0000000..95b6971 --- /dev/null +++ b/Vellum-3B-Ministral.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ecc2b0f4e652605c790eb6567e09e78dda2d50aaa72a59878f9677a5c258b7 +size 1968560480 diff --git a/Vellum-3B-Ministral.Q3_K_S.gguf b/Vellum-3B-Ministral.Q3_K_S.gguf new file mode 100644 index 0000000..7586bff --- /dev/null +++ b/Vellum-3B-Ministral.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2f102b27922ecae08f3b99770ebf11a0e2f7eb6871f374b4f5039c12d991b0 +size 1812158816 diff --git a/Vellum-3B-Ministral.Q4_K_M.gguf b/Vellum-3B-Ministral.Q4_K_M.gguf new file mode 100644 index 0000000..1a6de3a --- /dev/null +++ b/Vellum-3B-Ministral.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf766628b79706a77a3505f747fef73d22e1da0cfa814a62a745f0294572249 +size 2372983136 diff --git a/Vellum-3B-Ministral.Q4_K_S.gguf b/Vellum-3B-Ministral.Q4_K_S.gguf new file mode 100644 index 0000000..6bdbe17 --- /dev/null +++ b/Vellum-3B-Ministral.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70290dc218cc3bf3329e1aaead42ad9414028f8e1ad5ee6913fb04b2b368a64 +size 2279741792 diff --git a/Vellum-3B-Ministral.Q5_K_M.gguf b/Vellum-3B-Ministral.Q5_K_M.gguf new file mode 100644 index 0000000..829490b --- /dev/null +++ b/Vellum-3B-Ministral.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f3b54080f3bf0a1bebc7a8c17fc9885b6c8999be196a126a289ea3e709d605 +size 2750470496 diff --git a/Vellum-3B-Ministral.Q5_K_S.gguf b/Vellum-3B-Ministral.Q5_K_S.gguf new file mode 100644 index 0000000..2323417 --- /dev/null +++ b/Vellum-3B-Ministral.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d801a408ca98272cae1c81654b5bd7b13728f54a6f4162711b68db21169eb96 +size 2696157536 diff --git a/Vellum-3B-Ministral.Q6_K.gguf b/Vellum-3B-Ministral.Q6_K.gguf new file mode 100644 index 0000000..3347c42 --- /dev/null +++ b/Vellum-3B-Ministral.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5650599f1e5b5a11b86d4141956be48957baa989ba865d0cb1406143c1216c +size 3151550816 diff --git a/Vellum-3B-Ministral.Q8_0.gguf b/Vellum-3B-Ministral.Q8_0.gguf new file mode 100644 index 0000000..6932873 --- /dev/null +++ b/Vellum-3B-Ministral.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82cbeba35387756cf93887cab63528d38a0a04af0e8ff6059714ff77c83bd45c +size 4079491424 diff --git a/Vellum-3B-Ministral.f16.gguf b/Vellum-3B-Ministral.f16.gguf new file mode 100644 index 0000000..bf37618 --- /dev/null +++ b/Vellum-3B-Ministral.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62c4c7d7a0e2715e6ce2588ccc1c1a918897d8aa37e20a8d96a430aeb3ad676 +size 7671519584