commit 2710bfb3a157c56616f437dc7fdc88d8cb6027ef Author: ModelHub XC Date: Tue Sep 8 22:58:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37e9bb4 --- /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 +Mermaid-Llama-3-5B-Pruned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-5B-Pruned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mermaid-Llama-3-5B-Pruned.IQ4_XS.gguf b/Mermaid-Llama-3-5B-Pruned.IQ4_XS.gguf new file mode 100644 index 0000000..07fe4f2 --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6764b6c768dafec00e1231bcdc881d5d9166d0416fe2fbe8eb102830676643 +size 3067337312 diff --git a/Mermaid-Llama-3-5B-Pruned.Q2_K.gguf b/Mermaid-Llama-3-5B-Pruned.Q2_K.gguf new file mode 100644 index 0000000..6c1a9b0 --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4d9fbed176d5636dc5c169b7398192ecbd450e5da3870fb6167c119997f684 +size 2216139360 diff --git a/Mermaid-Llama-3-5B-Pruned.Q3_K_L.gguf b/Mermaid-Llama-3-5B-Pruned.Q3_K_L.gguf new file mode 100644 index 0000000..e00cba4 --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38196a48458f145ecd5a68de75a22661a28f905da5c775be73a87eddbffadeb0 +size 2950412896 diff --git a/Mermaid-Llama-3-5B-Pruned.Q3_K_M.gguf b/Mermaid-Llama-3-5B-Pruned.Q3_K_M.gguf new file mode 100644 index 0000000..87a8a8b --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ec1a738bd91e7aa5eb3d4234ae09f9732520af5840f9edd580562a207f59d5 +size 2759572064 diff --git a/Mermaid-Llama-3-5B-Pruned.Q3_K_S.gguf b/Mermaid-Llama-3-5B-Pruned.Q3_K_S.gguf new file mode 100644 index 0000000..a1ecfb0 --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8dd7d47e2c4beb82612224364e0489821406408b885013796276609e4969ee +size 2539502176 diff --git a/Mermaid-Llama-3-5B-Pruned.Q4_K_M.gguf b/Mermaid-Llama-3-5B-Pruned.Q4_K_M.gguf new file mode 100644 index 0000000..1c92b61 --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b76577b41560952395f6e6d4850889f61bed73da3287ef9216d029dfffc132 +size 3350813280 diff --git a/Mermaid-Llama-3-5B-Pruned.Q4_K_S.gguf b/Mermaid-Llama-3-5B-Pruned.Q4_K_S.gguf new file mode 100644 index 0000000..3fa8c9a --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f478acdb0189f5fe3a3892eeadad20f22d3790a2d5cbfb38c27712c0e79e5ee1 +size 3205388896 diff --git a/Mermaid-Llama-3-5B-Pruned.Q5_K_M.gguf b/Mermaid-Llama-3-5B-Pruned.Q5_K_M.gguf new file mode 100644 index 0000000..05ce1ed --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca191f8c0e7b4260604897f0758a5bf7e71d6cad3a6d16cb4bf3589653e4018a +size 3883096672 diff --git a/Mermaid-Llama-3-5B-Pruned.Q5_K_S.gguf b/Mermaid-Llama-3-5B-Pruned.Q5_K_S.gguf new file mode 100644 index 0000000..7ebe3fd --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f44a6c542d92cee4d612a86900562fac944326f93a856d36a7119002546395 +size 3799538272 diff --git a/Mermaid-Llama-3-5B-Pruned.Q6_K.gguf b/Mermaid-Llama-3-5B-Pruned.Q6_K.gguf new file mode 100644 index 0000000..dee4b8f --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabe5b1eed10837994270268be373fd05acfa164dfc4d7c82ed7a836b156097b +size 4448647776 diff --git a/Mermaid-Llama-3-5B-Pruned.Q8_0.gguf b/Mermaid-Llama-3-5B-Pruned.Q8_0.gguf new file mode 100644 index 0000000..24cb0cf --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf1101da771f48c5136ffd503e4b5845bf12a04e560b674a174fd3017ddbf57 +size 5759548000 diff --git a/Mermaid-Llama-3-5B-Pruned.f16.gguf b/Mermaid-Llama-3-5B-Pruned.f16.gguf new file mode 100644 index 0000000..1ca508e --- /dev/null +++ b/Mermaid-Llama-3-5B-Pruned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa02e3bdfe69fcd974755df15f7cd34047577e4d9b20aee2f726737055cf78db +size 10834000480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..02ac0fc --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: TroyDoesAI/Mermaid-Llama-3-5B-Pruned +language: +- en +library_name: transformers +license: cc-by-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TroyDoesAI/Mermaid-Llama-3-5B-Pruned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mermaid-Llama-3-5B-Pruned-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/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q2_K.gguf) | Q2_K | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q3_K_S.gguf) | Q3_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q3_K_L.gguf) | Q3_K_L | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.IQ4_XS.gguf) | IQ4_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q4_K_S.gguf) | Q4_K_S | 3.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q5_K_S.gguf) | Q5_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q5_K_M.gguf) | Q5_K_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q6_K.gguf) | Q6_K | 4.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.Q8_0.gguf) | Q8_0 | 5.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-5B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-5B-Pruned.f16.gguf) | f16 | 10.9 | 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. + +