commit bd4ef280f737999e7718780f793761fc122bb3c1 Author: ModelHub XC Date: Thu Sep 24 01:01:53 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a25992 --- /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-3-7B-Pruned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-7B-Pruned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mermaid-Llama-3-7B-Pruned.IQ4_XS.gguf b/Mermaid-Llama-3-7B-Pruned.IQ4_XS.gguf new file mode 100644 index 0000000..f9ac872 --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad47068867d5f2dcdf1dbcc6470c40a8c519ad66736100c8334aa899c34ebf2 +size 4008962848 diff --git a/Mermaid-Llama-3-7B-Pruned.Q2_K.gguf b/Mermaid-Llama-3-7B-Pruned.Q2_K.gguf new file mode 100644 index 0000000..7a09790 --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f0963781b0a0923f8519ee24ba0836fc9fb892471b242863c6d9a02ada844c +size 2858134304 diff --git a/Mermaid-Llama-3-7B-Pruned.Q3_K_L.gguf b/Mermaid-Llama-3-7B-Pruned.Q3_K_L.gguf new file mode 100644 index 0000000..c46150f --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e6396f76bd7fcaa986c5b1f44849e73632873fc9571519532ec58cb0d6df1b +size 3864775456 diff --git a/Mermaid-Llama-3-7B-Pruned.Q3_K_M.gguf b/Mermaid-Llama-3-7B-Pruned.Q3_K_M.gguf new file mode 100644 index 0000000..a8be9f0 --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87691647cb8a6c06bbcc6ca361a5f7943bafff40af24f5c5d699ca50ff09f69 +size 3594242848 diff --git a/Mermaid-Llama-3-7B-Pruned.Q3_K_S.gguf b/Mermaid-Llama-3-7B-Pruned.Q3_K_S.gguf new file mode 100644 index 0000000..763d3ef --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06bb21716f9e58d28dfb778cddd887c461c8d911ed8435b76fb46e62c75edb96 +size 3289500448 diff --git a/Mermaid-Llama-3-7B-Pruned.Q4_K_M.gguf b/Mermaid-Llama-3-7B-Pruned.Q4_K_M.gguf new file mode 100644 index 0000000..485bab9 --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb32cc9dbba9f8c93df154ee555e7d8611af62d9b80caca43a95e70693eb87c5 +size 4397427488 diff --git a/Mermaid-Llama-3-7B-Pruned.Q4_K_S.gguf b/Mermaid-Llama-3-7B-Pruned.Q4_K_S.gguf new file mode 100644 index 0000000..77df9dc --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ab419a389e25804060e430848569ab0f019518d3e368e88bfc785d4c7f2701 +size 4194462496 diff --git a/Mermaid-Llama-3-7B-Pruned.Q5_K_M.gguf b/Mermaid-Llama-3-7B-Pruned.Q5_K_M.gguf new file mode 100644 index 0000000..67f798c --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cbb40cb252624c9d3840624cc07e5924463411ae1796fba4bec78f8a64b77a +size 5116357408 diff --git a/Mermaid-Llama-3-7B-Pruned.Q5_K_S.gguf b/Mermaid-Llama-3-7B-Pruned.Q5_K_S.gguf new file mode 100644 index 0000000..db39803 --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ea9fb9df6f92167f2d80ad76f786a50c2d564ed3784810b7ba74898303ccbf +size 4999375648 diff --git a/Mermaid-Llama-3-7B-Pruned.Q6_K.gguf b/Mermaid-Llama-3-7B-Pruned.Q6_K.gguf new file mode 100644 index 0000000..e982a2c --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2d50c7a0b69bd001abb979605b2936f95bf0e08a4b4c1b9525046b407882ee +size 5880220448 diff --git a/Mermaid-Llama-3-7B-Pruned.Q8_0.gguf b/Mermaid-Llama-3-7B-Pruned.Q8_0.gguf new file mode 100644 index 0000000..69a1d8c --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51726453b54be7442ae84578abfd393083640de657cf8c44f31a218986e05ec +size 7613696800 diff --git a/Mermaid-Llama-3-7B-Pruned.f16.gguf b/Mermaid-Llama-3-7B-Pruned.f16.gguf new file mode 100644 index 0000000..660c3c7 --- /dev/null +++ b/Mermaid-Llama-3-7B-Pruned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53cc81a408f10d88fff7f8757846f40c8b6421789d1c05c764e7ff3c918607df +size 14323927840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5cb1ae4 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: TroyDoesAI/Mermaid-Llama-3-7B-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-3-7B-Pruned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mermaid-Llama-3-7B-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-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q3_K_L.gguf) | Q3_K_L | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.Q8_0.gguf) | Q8_0 | 7.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-7B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-7B-Pruned.f16.gguf) | f16 | 14.4 | 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. + +