commit 2d4c24b18e281cc2dcabe34323485051338148d5 Author: ModelHub XC Date: Tue Jul 7 09:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/M7-8B-passthrough-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d73c3df --- /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 +M7-8B-passthrough.f16.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +M7-8B-passthrough.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/M7-8B-passthrough.IQ4_XS.gguf b/M7-8B-passthrough.IQ4_XS.gguf new file mode 100644 index 0000000..edab3a5 --- /dev/null +++ b/M7-8B-passthrough.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ccf8acccece0f8c7e016fdaef48e6c112191a19be68805fd47c49c99bed9dc5 +size 5827641440 diff --git a/M7-8B-passthrough.Q2_K.gguf b/M7-8B-passthrough.Q2_K.gguf new file mode 100644 index 0000000..5f4911a --- /dev/null +++ b/M7-8B-passthrough.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04730455190da706135560fe387e286772b4fba86c706222e72168d5b7988413 +size 4003233888 diff --git a/M7-8B-passthrough.Q3_K_L.gguf b/M7-8B-passthrough.Q3_K_L.gguf new file mode 100644 index 0000000..be6e640 --- /dev/null +++ b/M7-8B-passthrough.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2a2450c81244c4c3a6c6f5071b5d62296e8ba2a587b81f8eca236642520161 +size 5650751584 diff --git a/M7-8B-passthrough.Q3_K_M.gguf b/M7-8B-passthrough.Q3_K_M.gguf new file mode 100644 index 0000000..589f88e --- /dev/null +++ b/M7-8B-passthrough.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c2c636b70f8591fc7e612f6c4852b526f57f8784ee0e01a4dc99165f80eaf0 +size 5195669600 diff --git a/M7-8B-passthrough.Q3_K_S.gguf b/M7-8B-passthrough.Q3_K_S.gguf new file mode 100644 index 0000000..d1348ea --- /dev/null +++ b/M7-8B-passthrough.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202d26695ddc099e55b37d747161e3a0e3ee5e37f46c81bf5cc913c35494b67b +size 4664565856 diff --git a/M7-8B-passthrough.Q4_0_4_4.gguf b/M7-8B-passthrough.Q4_0_4_4.gguf new file mode 100644 index 0000000..4c8bbc3 --- /dev/null +++ b/M7-8B-passthrough.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f911608ea71245627ddfb4a7ca214497aa601a0ffff84fa30dc748dfe2c745a5 +size 6072385632 diff --git a/M7-8B-passthrough.Q4_K_M.gguf b/M7-8B-passthrough.Q4_K_M.gguf new file mode 100644 index 0000000..e4dd226 --- /dev/null +++ b/M7-8B-passthrough.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee09279241daa54912a72705a4a66b3799da5642aa8a8fddf3d6ac41d2f11e21 +size 6461669472 diff --git a/M7-8B-passthrough.Q4_K_S.gguf b/M7-8B-passthrough.Q4_K_S.gguf new file mode 100644 index 0000000..e975b43 --- /dev/null +++ b/M7-8B-passthrough.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c266601717f19a155633281af9909b239cfe7251fa801a92ca1206eb46cde03 +size 6118522976 diff --git a/M7-8B-passthrough.Q5_K_M.gguf b/M7-8B-passthrough.Q5_K_M.gguf new file mode 100644 index 0000000..cc102d3 --- /dev/null +++ b/M7-8B-passthrough.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4164d97fae055406c3dd6152e8234259ecba07ae937b1f10a37e077da50987 +size 7597932640 diff --git a/M7-8B-passthrough.Q5_K_S.gguf b/M7-8B-passthrough.Q5_K_S.gguf new file mode 100644 index 0000000..4800137 --- /dev/null +++ b/M7-8B-passthrough.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c769e59d4ea489ab7aa97a695da589c7854d17aecef120588f5e97f13c5103 +size 7397392480 diff --git a/M7-8B-passthrough.Q6_K.gguf b/M7-8B-passthrough.Q6_K.gguf new file mode 100644 index 0000000..f36e8f7 --- /dev/null +++ b/M7-8B-passthrough.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f7d861dae876d1a4667d64a13f0142e61ff5484a3ccc8956c6e820b2d132db +size 8805212256 diff --git a/M7-8B-passthrough.Q8_0.gguf b/M7-8B-passthrough.Q8_0.gguf new file mode 100644 index 0000000..e32b4a4 --- /dev/null +++ b/M7-8B-passthrough.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305a73dbb513c0fde2054eaaaa7f2ea746f39ca5b6ac46970bdce1552f232488 +size 11404157024 diff --git a/M7-8B-passthrough.f16.gguf b/M7-8B-passthrough.f16.gguf new file mode 100644 index 0000000..ac20e50 --- /dev/null +++ b/M7-8B-passthrough.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fef60644429aef5c7c79db7453da413a267c3af784bc9a1070d6db250d7b322 +size 21464588384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0689cbe --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: allknowingroger/M7-8B-passthrough +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- liminerity/M7-7b +--- +## About + + + + + + +static quants of https://huggingface.co/allknowingroger/M7-8B-passthrough + + +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/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q3_K_S.gguf) | Q3_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q3_K_L.gguf) | Q3_K_L | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.IQ4_XS.gguf) | IQ4_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_0_4_4.gguf) | Q4_0_4_4 | 6.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q5_K_S.gguf) | Q5_K_S | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q5_K_M.gguf) | Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q6_K.gguf) | Q6_K | 8.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/M7-8B-passthrough-GGUF/resolve/main/M7-8B-passthrough.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. + +