commit 273b152c84f0a6f3a6b64ff6e470166b68f38295 Author: ModelHub XC Date: Wed Apr 22 12:22:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRMR-2B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3dbdeb9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +GRMR-2B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRMR-2B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRMR-2B-Instruct.IQ4_XS.gguf b/GRMR-2B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..4b1fda4 --- /dev/null +++ b/GRMR-2B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4c0eac71f7e2f061e8ee09f00fe8e34bad725e7c775c9ca12dcf70469bbff3 +size 1576204352 diff --git a/GRMR-2B-Instruct.Q2_K.gguf b/GRMR-2B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..9f92863 --- /dev/null +++ b/GRMR-2B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca09133c750386567ac34986993e244bc60466c9b2fc78a4994f8c42619c240 +size 1229830208 diff --git a/GRMR-2B-Instruct.Q3_K_L.gguf b/GRMR-2B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9627216 --- /dev/null +++ b/GRMR-2B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d6acfd61a865a820fd360c629657e67dfbf8dbaf5c21e06ef8fae8d7695e58f +size 1550436416 diff --git a/GRMR-2B-Instruct.Q3_K_M.gguf b/GRMR-2B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..f793319 --- /dev/null +++ b/GRMR-2B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6655127d41e20bdd97efa176db98db01ddf758b61ca32c48e933241382504a3d +size 1461667904 diff --git a/GRMR-2B-Instruct.Q3_K_S.gguf b/GRMR-2B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..8d7bf94 --- /dev/null +++ b/GRMR-2B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3c98b6179b385dfabe9802997a14c548d89077aa6447223744955d431db085e +size 1360660544 diff --git a/GRMR-2B-Instruct.Q4_0_4_4.gguf b/GRMR-2B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..877742f --- /dev/null +++ b/GRMR-2B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678f44cd1fd8d4aac2ed1a7304e322bb79a1de0c6cc3f770c41003af893b9913 +size 1629509696 diff --git a/GRMR-2B-Instruct.Q4_K_M.gguf b/GRMR-2B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f1cedd0 --- /dev/null +++ b/GRMR-2B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c52798f57dc3d63216fd400c8efc925b8f63ad052e181fd3bb0d1a584b8462b1 +size 1708582976 diff --git a/GRMR-2B-Instruct.Q4_K_S.gguf b/GRMR-2B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..2ea5ece --- /dev/null +++ b/GRMR-2B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7414ae23e755a0d596286c92d906a1f1a41c6444d1ee8759011ad69473686ba6 +size 1638651968 diff --git a/GRMR-2B-Instruct.Q5_K_M.gguf b/GRMR-2B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..1cee746 --- /dev/null +++ b/GRMR-2B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8626949d16aa0b2a2275f02e852f5ca04585d9fc3c6bf7b1badd04070447205a +size 1923278912 diff --git a/GRMR-2B-Instruct.Q5_K_S.gguf b/GRMR-2B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..504fa23 --- /dev/null +++ b/GRMR-2B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cba669706ee865677b3b2ac43511a8836af9f58e5f96b7967a3e1af72bacbcf +size 1882544192 diff --git a/GRMR-2B-Instruct.Q6_K.gguf b/GRMR-2B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..43c0ae0 --- /dev/null +++ b/GRMR-2B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14897349f0204546b9bf96df0bbc9782f89d6552f76a09a228c18554e08cab08 +size 2151393344 diff --git a/GRMR-2B-Instruct.Q8_0.gguf b/GRMR-2B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a56595a --- /dev/null +++ b/GRMR-2B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996b7c9f353f6de83c658e48d2241ac908e0161f779d0b22367de6773b2a2ae5 +size 2784495680 diff --git a/GRMR-2B-Instruct.f16.gguf b/GRMR-2B-Instruct.f16.gguf new file mode 100644 index 0000000..be503a8 --- /dev/null +++ b/GRMR-2B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a762399e3cf33f75294e37f7102d303c73947f323573fdf3bfd052f911febf7a +size 5235214400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d5902d7 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: qingy2024/GRMR-2B-Instruct +datasets: +- qingy2024/grmr-162k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/qingy2024/GRMR-2B-Instruct + + +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/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.7 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRMR-2B-Instruct-GGUF/resolve/main/GRMR-2B-Instruct.f16.gguf) | f16 | 5.3 | 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. + +