commit df0a5c44681c5f23a9ec6dbfebf890860a15805f Author: ModelHub XC Date: Thu Jun 18 17:12:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/merged-mermaid-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d4dff0 --- /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 +merged-mermaid-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +merged-mermaid-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a1b5cff --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mermaidchart/merged-mermaid-7b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mermaidchart/merged-mermaid-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#merged-mermaid-7b-GGUF).*** + +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/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/merged-mermaid-7b-GGUF/resolve/main/merged-mermaid-7b.f16.gguf) | f16 | 13.6 | 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. + + diff --git a/merged-mermaid-7b.IQ4_XS.gguf b/merged-mermaid-7b.IQ4_XS.gguf new file mode 100644 index 0000000..1cfed07 --- /dev/null +++ b/merged-mermaid-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38691f8190ea2ba206ece4cc84b11088920ffd8c0a766ba8cfca6886cca37638 +size 3647607200 diff --git a/merged-mermaid-7b.Q2_K.gguf b/merged-mermaid-7b.Q2_K.gguf new file mode 100644 index 0000000..6105e9c --- /dev/null +++ b/merged-mermaid-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c54a6f953ee13261542f19bd381c9b5c23bf4103f5847be9e322cc7cb4b929 +size 2532941216 diff --git a/merged-mermaid-7b.Q3_K_L.gguf b/merged-mermaid-7b.Q3_K_L.gguf new file mode 100644 index 0000000..5f60346 --- /dev/null +++ b/merged-mermaid-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17ddf52144e63be8532d11c57ce5a11bafd4bd0323b4314145145781ba3ac09 +size 3597195168 diff --git a/merged-mermaid-7b.Q3_K_M.gguf b/merged-mermaid-7b.Q3_K_M.gguf new file mode 100644 index 0000000..a141432 --- /dev/null +++ b/merged-mermaid-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf70470651d4cf767eec3d06f00cc81f3db8c6fa9fd4ec8054b59e57c79fadf6 +size 3298088864 diff --git a/merged-mermaid-7b.Q3_K_S.gguf b/merged-mermaid-7b.Q3_K_S.gguf new file mode 100644 index 0000000..aa2c616 --- /dev/null +++ b/merged-mermaid-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efcc0ef5b25e536086e0c86ffb43c4758d3fc10a698dcfcb187f25d651af158f +size 2948388768 diff --git a/merged-mermaid-7b.Q4_K_M.gguf b/merged-mermaid-7b.Q4_K_M.gguf new file mode 100644 index 0000000..3725cb0 --- /dev/null +++ b/merged-mermaid-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4526222a478ac3ab5a306452521d60d2410c2f240e2ae459e9c8af2c56e048ce +size 4081097120 diff --git a/merged-mermaid-7b.Q4_K_S.gguf b/merged-mermaid-7b.Q4_K_S.gguf new file mode 100644 index 0000000..5be983e --- /dev/null +++ b/merged-mermaid-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10b790cabc07087d2c156309a6f4b2607a0575f1c64385f1b3aecfb51261ce3 +size 3856832928 diff --git a/merged-mermaid-7b.Q5_K_M.gguf b/merged-mermaid-7b.Q5_K_M.gguf new file mode 100644 index 0000000..e6700e9 --- /dev/null +++ b/merged-mermaid-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27ef7336aff9ac9f7265dab61a1b0f463ed6ec0fc861f99fdd91b9362a74ffc +size 4783258016 diff --git a/merged-mermaid-7b.Q5_K_S.gguf b/merged-mermaid-7b.Q5_K_S.gguf new file mode 100644 index 0000000..97411ac --- /dev/null +++ b/merged-mermaid-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbf8d58fb5aededde117b9a3aba100753b02f9fdd1bf4bc93c072f6cae7ae38 +size 4651792800 diff --git a/merged-mermaid-7b.Q6_K.gguf b/merged-mermaid-7b.Q6_K.gguf new file mode 100644 index 0000000..161f81b --- /dev/null +++ b/merged-mermaid-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721afaab1a941d305e7ba7427c11105b0f610c90e06af3f8659f537c2983af0d +size 5529303968 diff --git a/merged-mermaid-7b.Q8_0.gguf b/merged-mermaid-7b.Q8_0.gguf new file mode 100644 index 0000000..594582e --- /dev/null +++ b/merged-mermaid-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3f3f40dfb257751ba7c217841fdee92e9b6d6d907d54a1b4aea9b524235cc5 +size 7161231264 diff --git a/merged-mermaid-7b.f16.gguf b/merged-mermaid-7b.f16.gguf new file mode 100644 index 0000000..3b4a603 --- /dev/null +++ b/merged-mermaid-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab01cef8d665a0ddd3b8abecbbb9515c66ad23966cd00a86e4be6a594846421b +size 13478369184