commit 1c90e9904fe5885342f19bd05a185c4ad0d08382 Author: ModelHub XC Date: Tue Aug 4 12:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gallium-350M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4b16083 --- /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 +Gallium-350M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gallium-350M.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gallium-350M.IQ4_XS.gguf b/Gallium-350M.IQ4_XS.gguf new file mode 100644 index 0000000..01863d8 --- /dev/null +++ b/Gallium-350M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d331fc9c8f828681506f843f5e8b7f7886ec903ef168eb2c2ff3b16b2748148b +size 210828896 diff --git a/Gallium-350M.Q2_K.gguf b/Gallium-350M.Q2_K.gguf new file mode 100644 index 0000000..7a64442 --- /dev/null +++ b/Gallium-350M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1053caecbd5d844abb81fcd86a54e30861e98016b825c3524039e0139b3685dc +size 159620704 diff --git a/Gallium-350M.Q3_K_L.gguf b/Gallium-350M.Q3_K_L.gguf new file mode 100644 index 0000000..7f369ee --- /dev/null +++ b/Gallium-350M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81e9c893977f13f6a536e84eadb46b5884f453ded6cd8367a96e8dc41ba7d6a +size 202071648 diff --git a/Gallium-350M.Q3_K_M.gguf b/Gallium-350M.Q3_K_M.gguf new file mode 100644 index 0000000..b9448db --- /dev/null +++ b/Gallium-350M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c164160ddb67f034150e9f268c64716207a2ffbc374be3abd3434d3c59f49a +size 192175712 diff --git a/Gallium-350M.Q3_K_S.gguf b/Gallium-350M.Q3_K_S.gguf new file mode 100644 index 0000000..b4cfd32 --- /dev/null +++ b/Gallium-350M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4655ffc4e36c3ad525e891dbc77bb5378bef9a24d8c5498173d148880f96cf0e +size 180174432 diff --git a/Gallium-350M.Q4_K_M.gguf b/Gallium-350M.Q4_K_M.gguf new file mode 100644 index 0000000..31601f8 --- /dev/null +++ b/Gallium-350M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04b79eed42b85cece1dfa01794573c6c6d1be20b541a43181ae72b9d8e5b72b +size 228335200 diff --git a/Gallium-350M.Q4_K_S.gguf b/Gallium-350M.Q4_K_S.gguf new file mode 100644 index 0000000..b3c397a --- /dev/null +++ b/Gallium-350M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfa453f9fb677fc40f643d44df208394fe80421b94457f693f0c02919de00e12 +size 219774560 diff --git a/Gallium-350M.Q5_K_M.gguf b/Gallium-350M.Q5_K_M.gguf new file mode 100644 index 0000000..e6d06ce --- /dev/null +++ b/Gallium-350M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fc636595093228002dea98d0d3f2d7b4ba3cc84d577da2cf2713ed607666a6 +size 259399264 diff --git a/Gallium-350M.Q5_K_S.gguf b/Gallium-350M.Q5_K_S.gguf new file mode 100644 index 0000000..0dbf635 --- /dev/null +++ b/Gallium-350M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e039721d2e1d14f8ca8fe44d3b41268c54b2c885df3fabcf623ab4cd073c77 +size 254246496 diff --git a/Gallium-350M.Q6_K.gguf b/Gallium-350M.Q6_K.gguf new file mode 100644 index 0000000..f1eb828 --- /dev/null +++ b/Gallium-350M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad61a652148e9a8b1b3942f8915b046d6776403a7028bfd7a77bd3c87fe8063 +size 292404832 diff --git a/Gallium-350M.Q8_0.gguf b/Gallium-350M.Q8_0.gguf new file mode 100644 index 0000000..37b3554 --- /dev/null +++ b/Gallium-350M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ae8fb0e32b2e5a967c80fdac319af6230e1224931d4fdb2af53f0a58883583 +size 377959360 diff --git a/Gallium-350M.f16.gguf b/Gallium-350M.f16.gguf new file mode 100644 index 0000000..b96345a --- /dev/null +++ b/Gallium-350M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d159a1f60916e12a0a621b19cd31c163b66bef9060b227cc5fea434957222e3 +size 709138240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa49242 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: DireDreadlord/Gallium-350M +datasets: +- Banaxi-Tech/Deepseek-V4-Reasoning-Code-2500 +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: lfm1.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- slm +- code +- reasoning +- chat +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DireDreadlord/Gallium-350M + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gallium-350M-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/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gallium-350M-GGUF/resolve/main/Gallium-350M.f16.gguf) | f16 | 0.8 | 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. + +