commit 3df42c737c6214be714e1044231b141f6673542d Author: ModelHub XC Date: Mon Apr 13 06:58:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mamba-790M-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9b056b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-790M.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mamba-790M.i1-IQ1_M.gguf b/Mamba-790M.i1-IQ1_M.gguf new file mode 100644 index 0000000..ec0deeb --- /dev/null +++ b/Mamba-790M.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a620a90aeea599b8493d1b0aa0a672b3bad2dc1d8dbbff1513164939fcec2964 +size 229485792 diff --git a/Mamba-790M.i1-IQ1_S.gguf b/Mamba-790M.i1-IQ1_S.gguf new file mode 100644 index 0000000..885c313 --- /dev/null +++ b/Mamba-790M.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc55f9d174341bdeb0ebaad5360ca4b663d4ac134d3e20598fce6963b914e55 +size 213118176 diff --git a/Mamba-790M.i1-IQ2_M.gguf b/Mamba-790M.i1-IQ2_M.gguf new file mode 100644 index 0000000..322b6df --- /dev/null +++ b/Mamba-790M.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15340f8bbad136b9496073a3e1a93a30a9d99c2eec8cdee0734dc1f1b7a0dd71 +size 300412128 diff --git a/Mamba-790M.i1-IQ2_S.gguf b/Mamba-790M.i1-IQ2_S.gguf new file mode 100644 index 0000000..aa70b56 --- /dev/null +++ b/Mamba-790M.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d8fcc9ceb26478d9e82926846eaed4bc2f81730f726aa33c2f225f9d035cb2 +size 278588640 diff --git a/Mamba-790M.i1-IQ2_XS.gguf b/Mamba-790M.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fa2f871 --- /dev/null +++ b/Mamba-790M.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a1409c60f4afe89a9e5441a71a989c0510da0e27e2f2936c77274979d14c2f +size 278588640 diff --git a/Mamba-790M.i1-IQ2_XXS.gguf b/Mamba-790M.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..179c8c5 --- /dev/null +++ b/Mamba-790M.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc76392641c0ee6e674ab16fbfbb563b3442131835db96d20fd86dc86e4d61c +size 256765152 diff --git a/Mamba-790M.i1-IQ3_M.gguf b/Mamba-790M.i1-IQ3_M.gguf new file mode 100644 index 0000000..cd0536e --- /dev/null +++ b/Mamba-790M.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08bc767a6282f591006eb3e6f46333f07cb8957e1412fa47ef6239b447f08d0 +size 387051456 diff --git a/Mamba-790M.i1-IQ3_S.gguf b/Mamba-790M.i1-IQ3_S.gguf new file mode 100644 index 0000000..41f6d9d --- /dev/null +++ b/Mamba-790M.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e44ba5be43c7129ef5c3959b6afee5de1964c102e7d373d4a4d678d2439e426 +size 387051456 diff --git a/Mamba-790M.i1-IQ3_XS.gguf b/Mamba-790M.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b908ad7 --- /dev/null +++ b/Mamba-790M.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a588f9245978ce8576dbb5112386fbb73a733308e9f59b1befce76ea535bcf +size 387051456 diff --git a/Mamba-790M.i1-IQ3_XXS.gguf b/Mamba-790M.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..072f72f --- /dev/null +++ b/Mamba-790M.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704324743a72fd172a3fae64f5fd64161afe66bdddbbc1ada1a32dddf8397e9a +size 344059104 diff --git a/Mamba-790M.i1-IQ4_XS.gguf b/Mamba-790M.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f2f1fdb --- /dev/null +++ b/Mamba-790M.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa16d01673b9b5f6fb7e1f24c92f460d8bb10436855eaac3d130ce654592ee8 +size 457977792 diff --git a/Mamba-790M.i1-Q2_K.gguf b/Mamba-790M.i1-Q2_K.gguf new file mode 100644 index 0000000..df28ae6 --- /dev/null +++ b/Mamba-790M.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cf16f2b39c86a92910cdf463735c65635459d7158c0578d988e9fb243060dc +size 316125120 diff --git a/Mamba-790M.i1-Q2_K_S.gguf b/Mamba-790M.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dd2fe66 --- /dev/null +++ b/Mamba-790M.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff71ae584a53bdba596938b9f553e2ed4b39c03e84699c225124849b3729835 +size 316125120 diff --git a/Mamba-790M.i1-Q3_K_L.gguf b/Mamba-790M.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9bf16e9 --- /dev/null +++ b/Mamba-790M.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e448edd0636ea5572a6e2a46d17b8b7d4f67b50cd608120472763ce4f2786e +size 387051456 diff --git a/Mamba-790M.i1-Q3_K_M.gguf b/Mamba-790M.i1-Q3_K_M.gguf new file mode 100644 index 0000000..380681c --- /dev/null +++ b/Mamba-790M.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daca6fcb5c3f23119ce40b5fca285717fdf1fc819f79849e35358d1d3b80562f +size 387051456 diff --git a/Mamba-790M.i1-Q3_K_S.gguf b/Mamba-790M.i1-Q3_K_S.gguf new file mode 100644 index 0000000..fac0837 --- /dev/null +++ b/Mamba-790M.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcae938739ae2aac9b81e1d94a34309ff367f92acdeeef6daf3fb45d4353827e +size 387051456 diff --git a/Mamba-790M.i1-Q4_0.gguf b/Mamba-790M.i1-Q4_0.gguf new file mode 100644 index 0000000..0436e49 --- /dev/null +++ b/Mamba-790M.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d31b267e8b476e75dc1e3d13b9f74eb87a33cf86074c800f232c32bc51d6b09 +size 479801280 diff --git a/Mamba-790M.i1-Q4_K_M.gguf b/Mamba-790M.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ed58586 --- /dev/null +++ b/Mamba-790M.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ddec759ccba9e2240e685d72cd479ba7b259c46687cd27ff92bd341bea3ce6 +size 481570752 diff --git a/Mamba-790M.i1-Q4_K_S.gguf b/Mamba-790M.i1-Q4_K_S.gguf new file mode 100644 index 0000000..781aab5 --- /dev/null +++ b/Mamba-790M.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:654ccea99873dffe68b56aeb4ba95125e5a8ccc38ab0914f146cf9e99a3aedb2 +size 481570752 diff --git a/Mamba-790M.i1-Q5_K_M.gguf b/Mamba-790M.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b70d099 --- /dev/null +++ b/Mamba-790M.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169dd174a3bb645490dda53f5e48dcb30b1e8a9a1f84506c18b1ca8ba65d6106 +size 569749440 diff --git a/Mamba-790M.i1-Q5_K_S.gguf b/Mamba-790M.i1-Q5_K_S.gguf new file mode 100644 index 0000000..85d5fb3 --- /dev/null +++ b/Mamba-790M.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed63c8f3edc8d4a7e25ddefbfbfcb8e5b134a92f189087500ba435447cf01347 +size 569749440 diff --git a/Mamba-790M.i1-Q6_K.gguf b/Mamba-790M.i1-Q6_K.gguf new file mode 100644 index 0000000..b382c32 --- /dev/null +++ b/Mamba-790M.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c56e8526c5494d043f6db1dc5656841dea892b8d99fc58a98ce84b632711ca1f +size 666922944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4eeff51 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Q-bert/Mamba-790M +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mamba-hf +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Q-bert/Mamba-790M + + +static quants are available at https://huggingface.co/mradermacher/Mamba-790M-GGUF +## 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/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ3_M.gguf) | i1-IQ3_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ3_S.gguf) | i1-IQ3_S | 0.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q4_0.gguf) | i1-Q4_0 | 0.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-790M-i1-GGUF/resolve/main/Mamba-790M.i1-Q6_K.gguf) | i1-Q6_K | 0.8 | practically like static Q6_K | + +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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..44420eb --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d587c3a7eb345731922ce5dd65eed282b0122f975e2538acce9c9f7687c211 +size 1499131