commit 35947439eeb542045581f6db12a3af15f70d12d5 Author: ModelHub XC Date: Thu Jun 18 14:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/marin-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9b7fde --- /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 +marin-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +marin-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cfd226e --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: marin-community/marin-8b-instruct +datasets: +- TIGER-Lab/AceCode-87K +- bespokelabs/Bespoke-Stratos-17k +- cognitivecomputations/dolphin-r1 +- tuenguyen/dolphin_r1_reasoning +- facebook/natural_reasoning +- open-r1/OpenThoughts-114k-math +- HuggingFaceTB/smoltalk +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +--- +## About + + + + + + + + + +static quants of https://huggingface.co/marin-community/marin-8b-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#marin-8b-instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/marin-8b-instruct-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/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/marin-8b-instruct-GGUF/resolve/main/marin-8b-instruct.f16.gguf) | f16 | 16.2 | 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/marin-8b-instruct.IQ4_XS.gguf b/marin-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..1d99ed5 --- /dev/null +++ b/marin-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d850bb3ac376d1a2610cd34a86045a61bc09bc440f6619e037d25fc0a880bd +size 4484367456 diff --git a/marin-8b-instruct.Q2_K.gguf b/marin-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..a783841 --- /dev/null +++ b/marin-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6868ffcd573045dae2bf73a31ff960b647a54b2335e36d1cb9294a1e0ecbca7 +size 3179136096 diff --git a/marin-8b-instruct.Q3_K_L.gguf b/marin-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..b72c868 --- /dev/null +++ b/marin-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c9cc60a0c63ec2b43219d2a4ae9729b3935a2bd18634c0f1fd4409375b3e54 +size 4321961056 diff --git a/marin-8b-instruct.Q3_K_M.gguf b/marin-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..5b50a5d --- /dev/null +++ b/marin-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebde71acbdd08153388122a37dbd75ae6626d0e35930cdd52cfeeaeda0153d8d +size 4018922592 diff --git a/marin-8b-instruct.Q3_K_S.gguf b/marin-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..8ceec47 --- /dev/null +++ b/marin-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d1f9c2b182d7a4f6871fdabb97646d93a516492d4db6b6e96b1e11eef543169 +size 3664503904 diff --git a/marin-8b-instruct.Q4_K_M.gguf b/marin-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..eb843f1 --- /dev/null +++ b/marin-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d035e1555cb75c110ab51db4dfd0e487838a536198dd7f6dc221625ec97a47 +size 4920738912 diff --git a/marin-8b-instruct.Q4_K_S.gguf b/marin-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..4f419c4 --- /dev/null +++ b/marin-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025ed97142048e0bd4419e28e7129dedf88af2831b33bd97309cfdff7a6130a0 +size 4692673632 diff --git a/marin-8b-instruct.Q5_K_M.gguf b/marin-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7c1399a --- /dev/null +++ b/marin-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853f4af30ba7fe2afdf55c45c5cfef7357b72747f61a7302d180cecf8db99fd1 +size 5732992096 diff --git a/marin-8b-instruct.Q5_K_S.gguf b/marin-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..37a18fc --- /dev/null +++ b/marin-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c62bdd48e774af9207a95efff34c0e864c2d35d9ef46ad52e8c6d0ac95e733 +size 5599298656 diff --git a/marin-8b-instruct.Q6_K.gguf b/marin-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..6ec20ff --- /dev/null +++ b/marin-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b5a4ec61dc678f5bd1686d9e218632e949bceeac5cc7f103908fdb04c0f99b +size 6596011104 diff --git a/marin-8b-instruct.Q8_0.gguf b/marin-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..3c539e3 --- /dev/null +++ b/marin-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e3efdd82094ad492015aad0d0f2acf3652fe3d76427915766ba812b10449d27 +size 8540775520 diff --git a/marin-8b-instruct.f16.gguf b/marin-8b-instruct.f16.gguf new file mode 100644 index 0000000..719f175 --- /dev/null +++ b/marin-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1702cbeda6aded481a2b7b02510046d39b3c64cc9e55dfa51b9034cf353e215c +size 16068895840