commit 25f71b06cf90b65c6344fbd9899b233b63100858 Author: ModelHub XC Date: Tue Sep 29 20:57:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bbfade --- /dev/null +++ b/.gitattributes @@ -0,0 +1,43 @@ +*.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-3-6B-Pruned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-6B-Pruned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mermaid-Llama-3-6B-Pruned.IQ3_XS.gguf b/Mermaid-Llama-3-6B-Pruned.IQ3_XS.gguf new file mode 100644 index 0000000..c3fb660 --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ad043dfac7759333d5e16f14053bd37baa83d48c0d2df21cb198f70d371f78 +size 2805699584 diff --git a/Mermaid-Llama-3-6B-Pruned.IQ4_XS.gguf b/Mermaid-Llama-3-6B-Pruned.IQ4_XS.gguf new file mode 100644 index 0000000..4d76341 --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad523ccae66e703297657588c03d1c6d22922d42b0a285b008d0f98a78f0273 +size 3543249920 diff --git a/Mermaid-Llama-3-6B-Pruned.Q3_K_M.gguf b/Mermaid-Llama-3-6B-Pruned.Q3_K_M.gguf new file mode 100644 index 0000000..bb0a95a --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26c449caaaacaf89b019dc8f68846e1e8a3c1269848b17ecb861d338751ba09 +size 3177419776 diff --git a/Mermaid-Llama-3-6B-Pruned.Q3_K_S.gguf b/Mermaid-Llama-3-6B-Pruned.Q3_K_S.gguf new file mode 100644 index 0000000..9bba226 --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f0e6b6788684f00258d763f21a8c8f5e5bf52714b0c00da43a7c8fc306c461 +size 2915013632 diff --git a/Mermaid-Llama-3-6B-Pruned.Q5_K_M.gguf b/Mermaid-Llama-3-6B-Pruned.Q5_K_M.gguf new file mode 100644 index 0000000..a1550f5 --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4339f0b0386c6863fb8030d431502bc5d6a627bd04ec9e872cd18a86f6c036c +size 4500239360 diff --git a/Mermaid-Llama-3-6B-Pruned.Q5_K_S.gguf b/Mermaid-Llama-3-6B-Pruned.Q5_K_S.gguf new file mode 100644 index 0000000..db6b03d --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97aae035019fa03777ee7d43bb0a1721f53748955c48afcb1120ee32322a0bee +size 4399969280 diff --git a/Mermaid-Llama-3-6B-Pruned.Q8_0.gguf b/Mermaid-Llama-3-6B-Pruned.Q8_0.gguf new file mode 100644 index 0000000..7f359c3 --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e5599e670be5b9743762f26243bf0f9d13eae7dc9eddf283c7d54205271ce8 +size 6687134720 diff --git a/Mermaid-Llama-3-6B-Pruned.f16.gguf b/Mermaid-Llama-3-6B-Pruned.f16.gguf new file mode 100644 index 0000000..df99d2a --- /dev/null +++ b/Mermaid-Llama-3-6B-Pruned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0429f4ca486051b272b37905aa9dc95e3739e107c5b4c9b2821a277eb86c5ef9 +size 12579476480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bab65ba --- /dev/null +++ b/README.md @@ -0,0 +1,59 @@ +--- +base_model: TroyDoesAI/Mermaid-Llama-3-6B-Pruned +language: +- en +library_name: transformers +license: cc-by-4.0 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/TroyDoesAI/Mermaid-Llama-3-6B-Pruned + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-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/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.Q8_0.gguf) | Q8_0 | 6.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-6B-Pruned-GGUF/resolve/main/Mermaid-Llama-3-6B-Pruned.f16.gguf) | f16 | 12.7 | 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. + +