commit 8a91106801c3b6f95502214f270b5cfc06a846a6 Author: ModelHub XC Date: Wed Jun 3 02:46:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..155acb6 --- /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 +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-INSTRUCT-8B-A0.6B-V2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.IQ4_XS.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.IQ4_XS.gguf new file mode 100644 index 0000000..bb5dce3 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2670c035cf0573ffea97f96cee45a0662979f579f90b1b9f80422908b5565c30 +size 4456137952 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q2_K.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q2_K.gguf new file mode 100644 index 0000000..4badc75 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefe9140ea1190c02ab0123d18d160001d03676e20bfdf7795bb90a63de5b63f +size 3340289248 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_L.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_L.gguf new file mode 100644 index 0000000..b8c6775 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c199b4a18e7cfaaa23acbb73dcd014f0113f58a20ca3ea7eec7bbe327712d08 +size 4369728736 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_M.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_M.gguf new file mode 100644 index 0000000..ba8b3fb --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef74e3d00674728f79a716d115fe2d5c364273faa48c507ca67a45121865dec +size 4205036768 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_S.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_S.gguf new file mode 100644 index 0000000..b95bce1 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2334c66ec91887ed3b80188c67f3d5dbb6dd348ac6b5da6fc3c772225bb3639 +size 3868083424 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_M.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_M.gguf new file mode 100644 index 0000000..c5dcc9d --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5dbfc95663f10733f8c7562b73365952dd56af924fbcec27a2470473bc37863 +size 5371987168 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_S.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_S.gguf new file mode 100644 index 0000000..b37d319 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af009c274814595f5154df2deb13d0ffc3268b71faf439d1f50f9e3bc36f6b11 +size 4906894560 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_M.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_M.gguf new file mode 100644 index 0000000..a01b848 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fbf60044bd0896836dae203e02f0c1bd0f1499cd1a4c1a86a65ce4a7cb73ac7 +size 6110577888 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_S.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_S.gguf new file mode 100644 index 0000000..654f4a5 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10591d3faa58b3165e83a127ba4d125ab823ef1dbba213f66557666603b29509 +size 5709513952 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q6_K.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q6_K.gguf new file mode 100644 index 0000000..1b2f2a6 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5beb5441cbde3e5497dbb9ed9af451fffe7b4cb7a893abfa687d8947f1ce2dbc +size 7209632992 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q8_0.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q8_0.gguf new file mode 100644 index 0000000..f8b93f8 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe596f5812a4d8199ad203c3f31186cf65dcab501d946adf0ffc02140e2ee111 +size 8527231200 diff --git a/Marco-Nano-INSTRUCT-8B-A0.6B-V2.f16.gguf b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.f16.gguf new file mode 100644 index 0000000..015f808 --- /dev/null +++ b/Marco-Nano-INSTRUCT-8B-A0.6B-V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2365abd4650d019b17a062cbed1f5a0e1666730de05f2e57cbaf2706dcf548ba +size 16022296800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..053bbce --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: DavidAU/Marco-Nano-INSTRUCT-8B-A0.6B-V2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- finetune +- unsloth +- moe +- sparse moe +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/Marco-Nano-INSTRUCT-8B-A0.6B-V2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-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/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_M.gguf) | Q3_K_M | 4.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_S.gguf) | Q4_K_S | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-INSTRUCT-8B-A0.6B-V2-GGUF/resolve/main/Marco-Nano-INSTRUCT-8B-A0.6B-V2.f16.gguf) | f16 | 16.1 | 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. + +