commit f54471f1b016da2bae9c8ae0e4e1ad5e70a45267 Author: ModelHub XC Date: Tue Jul 21 22:20:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MinLlama-3-8B-instruct-pass-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e870ce --- /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 +MinLlama-3-8B-instruct-pass.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.f16.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MinLlama-3-8B-instruct-pass.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MinLlama-3-8B-instruct-pass.IQ3_M.gguf b/MinLlama-3-8B-instruct-pass.IQ3_M.gguf new file mode 100644 index 0000000..e2af2d7 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f457d75c762d0225e31e05a6691bab5a3759aced6ebd52a1e558b3f03475bbc3 +size 2803875296 diff --git a/MinLlama-3-8B-instruct-pass.IQ3_S.gguf b/MinLlama-3-8B-instruct-pass.IQ3_S.gguf new file mode 100644 index 0000000..ad7d3b3 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44501dc95456fa759544264c1d5b82493956a39ebe94c179377c37875777d97d +size 2739256800 diff --git a/MinLlama-3-8B-instruct-pass.IQ3_XS.gguf b/MinLlama-3-8B-instruct-pass.IQ3_XS.gguf new file mode 100644 index 0000000..25f02d3 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a350038f0e9ec58edf1086ee3ff25d5ca60f74024c27918a1465d7cff9fc673 +size 2624044512 diff --git a/MinLlama-3-8B-instruct-pass.IQ4_XS.gguf b/MinLlama-3-8B-instruct-pass.IQ4_XS.gguf new file mode 100644 index 0000000..b99e9ca --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b3b33c3b0642dd27fa82c03a26d8f7a647d93ea353b5eddfd16b072760db3b +size 3300449760 diff --git a/MinLlama-3-8B-instruct-pass.Q2_K.gguf b/MinLlama-3-8B-instruct-pass.Q2_K.gguf new file mode 100644 index 0000000..7fa65bc --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5647ad9a2c3a09a08069032660cf4543e0292160201efc9c942e41d1b790f5f7 +size 2376637920 diff --git a/MinLlama-3-8B-instruct-pass.Q3_K_L.gguf b/MinLlama-3-8B-instruct-pass.Q3_K_L.gguf new file mode 100644 index 0000000..786fba5 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d7f0d3d4f82f596eb668e33c87a0f183f0814845ac987bd6e50eae3de73fad +size 3179003360 diff --git a/MinLlama-3-8B-instruct-pass.Q3_K_M.gguf b/MinLlama-3-8B-instruct-pass.Q3_K_M.gguf new file mode 100644 index 0000000..1dd7148 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ec8b1e7e80f25dbd6c471234ff505c2822304e955ea88bc8071c22cd3b07821 +size 2968239584 diff --git a/MinLlama-3-8B-instruct-pass.Q3_K_S.gguf b/MinLlama-3-8B-instruct-pass.Q3_K_S.gguf new file mode 100644 index 0000000..58c8903 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcad8e6e5ccbc6e0c06562dc16554e4fc22a211e48930dbac94b5d0d28eb533c +size 2727001568 diff --git a/MinLlama-3-8B-instruct-pass.Q4_K_M.gguf b/MinLlama-3-8B-instruct-pass.Q4_K_M.gguf new file mode 100644 index 0000000..e00177b --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fcea92592b95411aa5a62179cdd0dae26accbd038b5e4663204ba412065f0a3 +size 3596246496 diff --git a/MinLlama-3-8B-instruct-pass.Q4_K_S.gguf b/MinLlama-3-8B-instruct-pass.Q4_K_S.gguf new file mode 100644 index 0000000..48a8242 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0260b220a9a2af2417559f273cf598937bde9be516c0e7c91d9852ff847a2bf8 +size 3450822112 diff --git a/MinLlama-3-8B-instruct-pass.Q5_K_M.gguf b/MinLlama-3-8B-instruct-pass.Q5_K_M.gguf new file mode 100644 index 0000000..bf3fc02 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a4adeb987760af71ef94cdeab0f91285c0ce6ab8d41f176691b1923637c36a +size 4183055840 diff --git a/MinLlama-3-8B-instruct-pass.Q5_K_S.gguf b/MinLlama-3-8B-instruct-pass.Q5_K_S.gguf new file mode 100644 index 0000000..4e01e8e --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef0f9fad52c1aa6d4c80792ea066a89cc63c33eb88b566a95167381b308d50b +size 4099497440 diff --git a/MinLlama-3-8B-instruct-pass.Q6_K.gguf b/MinLlama-3-8B-instruct-pass.Q6_K.gguf new file mode 100644 index 0000000..eb6141b --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2833880932b36ad744a3345741af9c465401b76cdeb30a2990ebe7d110a6bfe4 +size 4806540768 diff --git a/MinLlama-3-8B-instruct-pass.Q8_0.gguf b/MinLlama-3-8B-instruct-pass.Q8_0.gguf new file mode 100644 index 0000000..4909e59 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01ee375a268db59aa26665b8b03576d04f3ad0d09facd236eb49e9f99fedcd8 +size 6223085024 diff --git a/MinLlama-3-8B-instruct-pass.f16.gguf b/MinLlama-3-8B-instruct-pass.f16.gguf new file mode 100644 index 0000000..65b8994 --- /dev/null +++ b/MinLlama-3-8B-instruct-pass.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463716b5bc05a157f4e9d44e397805aee09ca3606afdf219b7e3b66b07c01324 +size 11706482144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a8ec24d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: JoPmt/MinLlama-3-8B-instruct-pass +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- NousResearch/Meta-Llama-3-8B-Instruct +--- +## About + + + + + + +static quants of https://huggingface.co/JoPmt/MinLlama-3-8B-instruct-pass + + +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/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q2_K.gguf) | Q2_K | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.IQ3_XS.gguf) | IQ3_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q3_K_S.gguf) | Q3_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.IQ3_S.gguf) | IQ3_S | 2.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.IQ3_M.gguf) | IQ3_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q3_K_L.gguf) | Q3_K_L | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.IQ4_XS.gguf) | IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q4_K_M.gguf) | Q4_K_M | 3.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q5_K_S.gguf) | Q5_K_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q5_K_M.gguf) | Q5_K_M | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q6_K.gguf) | Q6_K | 4.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.Q8_0.gguf) | Q8_0 | 6.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MinLlama-3-8B-instruct-pass-GGUF/resolve/main/MinLlama-3-8B-instruct-pass.f16.gguf) | f16 | 11.8 | 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. + +