commit 3576792056b641efc5bb7b60b0cad8302daab720 Author: ModelHub XC Date: Sun Sep 27 22:00:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..354f064 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-3-8B-SNR-LASER.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mermaid-Llama-3-8B-SNR-LASER.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mermaid-Llama-3-8B-SNR-LASER.IQ3_M.gguf b/Mermaid-Llama-3-8B-SNR-LASER.IQ3_M.gguf new file mode 100644 index 0000000..d0da9d0 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf105812981574009de77db3cb1456c99cb5165653c15fdf3dc6c518828806e +size 3785336096 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.IQ3_S.gguf b/Mermaid-Llama-3-8B-SNR-LASER.IQ3_S.gguf new file mode 100644 index 0000000..e46550d --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9161b705d7a780e2513bb166ef983e2e593145d006d351ff3b5de1ce309516a2 +size 3682837792 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.IQ3_XS.gguf b/Mermaid-Llama-3-8B-SNR-LASER.IQ3_XS.gguf new file mode 100644 index 0000000..9c85e8d --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91b456947e1cddfb517b96ca71cf274975752538debd906584919cf01c31cee +size 3519259936 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.IQ4_XS.gguf b/Mermaid-Llama-3-8B-SNR-LASER.IQ4_XS.gguf new file mode 100644 index 0000000..9942af3 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2e3bbdccb1fc5d6a82737fb4846d6373c337520af6d0a17a5c7ed2aad1b953 +size 4484875552 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q2_K.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q2_K.gguf new file mode 100644 index 0000000..abffbea --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeadd34ed99ec8d78c74f3dbb68cceb61ad63c815f80cf80f77f67d6abe4e9a9 +size 3179644192 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_L.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_L.gguf new file mode 100644 index 0000000..27df229 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9672d88be1cb7e00bd59aa1440d076336d77889a9c5f8c48b7a662b74e359e +size 4322469152 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_M.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_M.gguf new file mode 100644 index 0000000..242fbf6 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9b991642bc83cd78f802d67086b3abfd3d7249b058066ec7719177d080d306 +size 4019430688 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_S.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_S.gguf new file mode 100644 index 0000000..355a2f6 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12d60db2a88250d2aa7a6f9841eb7940ab688c7f02c10ec0da4714f50e977ad +size 3665012000 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_M.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_M.gguf new file mode 100644 index 0000000..fad1f99 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80ca3eecb86f508b60d08e035ea8ec4fb7a2a5bab375cbab0c26f4b2197e5957 +size 4921247008 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_S.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_S.gguf new file mode 100644 index 0000000..1fb56b1 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee772a7f93c694e6f3cd6f72e09621209ba2b0ba13dc15f51a9575b2a97be8c +size 4693181728 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_M.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_M.gguf new file mode 100644 index 0000000..d968864 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a88cc991e12018b0cd17278cd82c24669105208a9bda8c89b34facf766dbf59 +size 5733500192 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_S.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_S.gguf new file mode 100644 index 0000000..13bbe59 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f84c3339b756f2d83ad8e15cbec728f12325a37a5f3e0e6c5787c334625d24 +size 5599806752 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q6_K.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q6_K.gguf new file mode 100644 index 0000000..95896fe --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a921e50ef8b5fc22e160cbadfed259936624eb34f56966c13a25df43b560ad0c +size 6596519200 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.Q8_0.gguf b/Mermaid-Llama-3-8B-SNR-LASER.Q8_0.gguf new file mode 100644 index 0000000..9da2387 --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503e82c39e3c3cad97eea87807dfcc176bdce9e5adefdb0f2e1c7a011fce858d +size 8541283616 diff --git a/Mermaid-Llama-3-8B-SNR-LASER.f16.gguf b/Mermaid-Llama-3-8B-SNR-LASER.f16.gguf new file mode 100644 index 0000000..18ba2fb --- /dev/null +++ b/Mermaid-Llama-3-8B-SNR-LASER.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5d4a6090067cafaa4ef138a0e7f6a998fb514ae511bf9d245ef77dcb1d5424 +size 16069403936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9937628 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: TroyDoesAI/Mermaid-Llama-3-8B-SNR-LASER +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/TroyDoesAI/Mermaid-Llama-3-8B-SNR-LASER + + +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-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mermaid-Llama-3-8B-SNR-LASER-GGUF/resolve/main/Mermaid-Llama-3-8B-SNR-LASER.f16.gguf) | f16 | 16.2 | 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. + +