commit d26acd9e48c313770e27b3b3746000e0a26ac269 Author: ModelHub XC Date: Sun May 10 21:36:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gplm-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a05169 --- /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 +gplm-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gplm-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b016af --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Shinapri/gplm-3b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Shinapri/gplm-3b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gplm-3b-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/gplm-3b-GGUF/resolve/main/gplm-3b.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gplm-3b-GGUF/resolve/main/gplm-3b.f16.gguf) | f16 | 6.5 | 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/gplm-3b.IQ4_XS.gguf b/gplm-3b.IQ4_XS.gguf new file mode 100644 index 0000000..7a31890 --- /dev/null +++ b/gplm-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afac64db97f15956699fc15ac889c20c1331ce8f4ea92ea2fd84b8f04ba0efc9 +size 1840906912 diff --git a/gplm-3b.Q2_K.gguf b/gplm-3b.Q2_K.gguf new file mode 100644 index 0000000..8839213 --- /dev/null +++ b/gplm-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03a8276fe558840473f47df1e2d3864598154ea2dcc75851bc776255abdb34b8 +size 1363935904 diff --git a/gplm-3b.Q3_K_L.gguf b/gplm-3b.Q3_K_L.gguf new file mode 100644 index 0000000..395ad83 --- /dev/null +++ b/gplm-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b3258c02e998223097e82c95fea44e6bb876aab18bb6c8072de38d7eccf3ce +size 1815347872 diff --git a/gplm-3b.Q3_K_M.gguf b/gplm-3b.Q3_K_M.gguf new file mode 100644 index 0000000..d7e21d3 --- /dev/null +++ b/gplm-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ececbec817e0475c706bcf8e9bc7e6e6c100ae0064fd1a0e5e918362ea7404bd +size 1687159456 diff --git a/gplm-3b.Q3_K_S.gguf b/gplm-3b.Q3_K_S.gguf new file mode 100644 index 0000000..7b24e4f --- /dev/null +++ b/gplm-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5df9d85f0a91b072828daea6a648a53ac9db61bbca984b8c02ef8f8aab77785 +size 1542849184 diff --git a/gplm-3b.Q4_K_M.gguf b/gplm-3b.Q4_K_M.gguf new file mode 100644 index 0000000..b2ee3e2 --- /dev/null +++ b/gplm-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b00b3e527f79fa02edf1b1953ac3612f5c0c3524c4904816e2d2c7fe43d240a +size 2019377824 diff --git a/gplm-3b.Q4_K_S.gguf b/gplm-3b.Q4_K_S.gguf new file mode 100644 index 0000000..817e8a2 --- /dev/null +++ b/gplm-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bae7870108eddc999523d92f990b2f83642355171c9870d3041d0ba4ebf42ca +size 1928200864 diff --git a/gplm-3b.Q5_K_M.gguf b/gplm-3b.Q5_K_M.gguf new file mode 100644 index 0000000..ee0e6a1 --- /dev/null +++ b/gplm-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1a87683285db4f95d8a4a782830bfb498dcf238e09c4fcc400e77d924bb213 +size 2322154144 diff --git a/gplm-3b.Q5_K_S.gguf b/gplm-3b.Q5_K_S.gguf new file mode 100644 index 0000000..20bb053 --- /dev/null +++ b/gplm-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7680274bd8d7df5bcc036d9098e5b32f3b5af0a331df8233607727967da45373 +size 2269512352 diff --git a/gplm-3b.Q6_K.gguf b/gplm-3b.Q6_K.gguf new file mode 100644 index 0000000..0e5c6bc --- /dev/null +++ b/gplm-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47dd2ea3be2753661bd5be3c9c526fa310f936ad38d4ad25c74544d4dc47fa1f +size 2643853984 diff --git a/gplm-3b.Q8_0.gguf b/gplm-3b.Q8_0.gguf new file mode 100644 index 0000000..fcf01ee --- /dev/null +++ b/gplm-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0993ac74b939febc1d47e53c540d8f22f6cf25be7af4b7a6df84b418864cf5f5 +size 3421899424 diff --git a/gplm-3b.f16.gguf b/gplm-3b.f16.gguf new file mode 100644 index 0000000..00c4a72 --- /dev/null +++ b/gplm-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985c0bfda61eaf69949c89b74b311c69dcaa01f830d432d5adb33cb010cf11c4 +size 6433688224