commit caeee1b77c4e2709a08199b101d35221b1e055dc Author: ModelHub XC Date: Mon Apr 27 14:24:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/rubra-11b-h-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7ce93f --- /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 +rubra-11b-h.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.f16.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +rubra-11b-h.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5c1ea8 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: sanjay920/rubra-11b-h +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- freeze +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/sanjay920/rubra-11b-h + + +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/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q3_K_S.gguf) | Q3_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q3_K_L.gguf) | Q3_K_L | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.IQ4_XS.gguf) | IQ4_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q4_0_4_4.gguf) | Q4_0_4_4 | 6.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q5_K_S.gguf) | Q5_K_S | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q5_K_M.gguf) | Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q6_K.gguf) | Q6_K | 8.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/rubra-11b-h-GGUF/resolve/main/rubra-11b-h.f16.gguf) | f16 | 21.6 | 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. + + diff --git a/rubra-11b-h.IQ4_XS.gguf b/rubra-11b-h.IQ4_XS.gguf new file mode 100644 index 0000000..6415a58 --- /dev/null +++ b/rubra-11b-h.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d92b7ef0cbb0c84023e33a76f3949434d754f59ed7f776d1b57d315befec3e14 +size 5827641248 diff --git a/rubra-11b-h.Q2_K.gguf b/rubra-11b-h.Q2_K.gguf new file mode 100644 index 0000000..8ed5605 --- /dev/null +++ b/rubra-11b-h.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a56e25971e379b960c9608ec14fca89e97eb39a8aa7cdc2c8846975d7afbf14 +size 4003233696 diff --git a/rubra-11b-h.Q3_K_L.gguf b/rubra-11b-h.Q3_K_L.gguf new file mode 100644 index 0000000..a93754a --- /dev/null +++ b/rubra-11b-h.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a92fcdbaa2f7240f235a7ff2bd2b8525dca85cc0ea4b01ddff95fd38b8a992d +size 5650751392 diff --git a/rubra-11b-h.Q3_K_M.gguf b/rubra-11b-h.Q3_K_M.gguf new file mode 100644 index 0000000..fec4be5 --- /dev/null +++ b/rubra-11b-h.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32ad70f29edbffa302e65af130bc3a1197303c565d1685f69a38e6817210fc6 +size 5195669408 diff --git a/rubra-11b-h.Q3_K_S.gguf b/rubra-11b-h.Q3_K_S.gguf new file mode 100644 index 0000000..16c4b2d --- /dev/null +++ b/rubra-11b-h.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a955fa175a56477e06e9c2576526369824f383a4c7f815b59ede897d9c71bb83 +size 4664565664 diff --git a/rubra-11b-h.Q4_0_4_4.gguf b/rubra-11b-h.Q4_0_4_4.gguf new file mode 100644 index 0000000..aa2e413 --- /dev/null +++ b/rubra-11b-h.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1d7d9880b7ab8f9f9df15ff40120b03e574ae746d9b66cb3b59b0c6ca17022 +size 6072385440 diff --git a/rubra-11b-h.Q4_K_M.gguf b/rubra-11b-h.Q4_K_M.gguf new file mode 100644 index 0000000..bbed648 --- /dev/null +++ b/rubra-11b-h.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60be33aa7e2605726f171c5f05ef77242b9fbd7acad5a16aee68dad4664ef03 +size 6461669280 diff --git a/rubra-11b-h.Q4_K_S.gguf b/rubra-11b-h.Q4_K_S.gguf new file mode 100644 index 0000000..d1b8db7 --- /dev/null +++ b/rubra-11b-h.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68a903fd90521aa151c154567d669d929e62226f401140c74d128db49c51114 +size 6118522784 diff --git a/rubra-11b-h.Q5_K_M.gguf b/rubra-11b-h.Q5_K_M.gguf new file mode 100644 index 0000000..e4aff15 --- /dev/null +++ b/rubra-11b-h.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad1e363d700c2f5aadf46c1feb9b87211318a96bd70d662240b89df052078bc +size 7597932448 diff --git a/rubra-11b-h.Q5_K_S.gguf b/rubra-11b-h.Q5_K_S.gguf new file mode 100644 index 0000000..19bcdcb --- /dev/null +++ b/rubra-11b-h.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f7d518050eb5eb4bb5274cf0604105ca1099e2152a1e4df450c8255a93923d +size 7397392288 diff --git a/rubra-11b-h.Q6_K.gguf b/rubra-11b-h.Q6_K.gguf new file mode 100644 index 0000000..b80a784 --- /dev/null +++ b/rubra-11b-h.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a4699f16c68807309e36d82e0b2ad9e0b3351e425d1caff6929857b48b2f82 +size 8805212064 diff --git a/rubra-11b-h.Q8_0.gguf b/rubra-11b-h.Q8_0.gguf new file mode 100644 index 0000000..d1c2e48 --- /dev/null +++ b/rubra-11b-h.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9f626561255e87341816d2128e183368b00bf98c383306a129d960894fb07c +size 11404156832 diff --git a/rubra-11b-h.f16.gguf b/rubra-11b-h.f16.gguf new file mode 100644 index 0000000..34fa89d --- /dev/null +++ b/rubra-11b-h.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd1784f9fef114a35561ae8629bcc45bc53870b0256c3d515d17610d99a8854 +size 21464588192