commit df3f0f876ddd39d59a32c386574090c5aa7225b3 Author: ModelHub XC Date: Wed Apr 29 16:37:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mamba-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6bfdd6d --- /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 +Mamba-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mamba-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mamba-3B.IQ4_XS.gguf b/Mamba-3B.IQ4_XS.gguf new file mode 100644 index 0000000..404f0d2 --- /dev/null +++ b/Mamba-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74766aa2a0cc8844aa62caac1362b67fa71f2dc51320af511d979c099c2d224b +size 1538053888 diff --git a/Mamba-3B.Q2_K.gguf b/Mamba-3B.Q2_K.gguf new file mode 100644 index 0000000..4dbf634 --- /dev/null +++ b/Mamba-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd6f23e69e9f50e27a756dce376e91e474442ce5f2f27ab07fbddabff95b81a +size 1014093568 diff --git a/Mamba-3B.Q3_K_L.gguf b/Mamba-3B.Q3_K_L.gguf new file mode 100644 index 0000000..138a2b5 --- /dev/null +++ b/Mamba-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f2ec67cbc8b07b1f5000da215c5d59c7ec5521662ea400462049615b9b226b +size 1276073728 diff --git a/Mamba-3B.Q3_K_M.gguf b/Mamba-3B.Q3_K_M.gguf new file mode 100644 index 0000000..2f772a9 --- /dev/null +++ b/Mamba-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823c688e086bb9aa3c25ecd7bb2e285fbc2ea0ae86fbdf08475f64ede6c46b66 +size 1276073728 diff --git a/Mamba-3B.Q3_K_S.gguf b/Mamba-3B.Q3_K_S.gguf new file mode 100644 index 0000000..68f193a --- /dev/null +++ b/Mamba-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e9308ed5a76a58c90ee5509bf882dc9275be85e37ba52814454fa39ec007bf +size 1276073728 diff --git a/Mamba-3B.Q4_K_M.gguf b/Mamba-3B.Q4_K_M.gguf new file mode 100644 index 0000000..b127d8d --- /dev/null +++ b/Mamba-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6411123793e3129baf8ccab518c7c83899d64e881b18d6e902774c328762ac14 +size 1625216768 diff --git a/Mamba-3B.Q4_K_S.gguf b/Mamba-3B.Q4_K_S.gguf new file mode 100644 index 0000000..65a0ad6 --- /dev/null +++ b/Mamba-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ade8ff7c3f360a8ce988f20a04e8234d79b93e9d8bc07ffa11d8a75b44c7f5 +size 1625216768 diff --git a/Mamba-3B.Q5_K_M.gguf b/Mamba-3B.Q5_K_M.gguf new file mode 100644 index 0000000..185f6d1 --- /dev/null +++ b/Mamba-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f74cb3bb56aa379eda476a73eb2e95cefadfb96d950d9199431e854642a61a6 +size 1950930688 diff --git a/Mamba-3B.Q5_K_S.gguf b/Mamba-3B.Q5_K_S.gguf new file mode 100644 index 0000000..d667e58 --- /dev/null +++ b/Mamba-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e257ad9ff47a2acae0f4d55f4be966aa8c152089a526b17eb05b20ca8bdef6 +size 1950930688 diff --git a/Mamba-3B.Q6_K.gguf b/Mamba-3B.Q6_K.gguf new file mode 100644 index 0000000..afe6408 --- /dev/null +++ b/Mamba-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fccb3444e6a5c6996b534e8069661537191e848483090d8ab6150f34e7fbdb12 +size 2309904128 diff --git a/Mamba-3B.Q8_0.gguf b/Mamba-3B.Q8_0.gguf new file mode 100644 index 0000000..f363b78 --- /dev/null +++ b/Mamba-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d566660898f04363132b4aee285e5e99d5fd857f9b9e1c99a0e8d4e00ba9fd9 +size 2965799648 diff --git a/Mamba-3B.f16.gguf b/Mamba-3B.f16.gguf new file mode 100644 index 0000000..83d1355 --- /dev/null +++ b/Mamba-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23849a70c76062729b4eb74859c9a3e5f490683b831a5a795ad9bbe84696ba00 +size 5553902048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..62fbd13 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Q-bert/Mamba-3B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mamba-hf +--- +## About + + + + + + +static quants of https://huggingface.co/Q-bert/Mamba-3B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mamba-3B-i1-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-3B-GGUF/resolve/main/Mamba-3B.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q3_K_L.gguf) | Q3_K_L | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q5_K_S.gguf) | Q5_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q6_K.gguf) | Q6_K | 2.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.Q8_0.gguf) | Q8_0 | 3.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mamba-3B-GGUF/resolve/main/Mamba-3B.f16.gguf) | f16 | 5.7 | 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. + +