commit 1c2bcff448c45057a953af3a2d24a223fcaa48d2 Author: ModelHub XC Date: Sun Jul 19 07:33:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-8B-ScaleQuest-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..59594a8 --- /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 +Llama3-8B-ScaleQuest.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-8B-ScaleQuest.IQ4_XS.gguf b/Llama3-8B-ScaleQuest.IQ4_XS.gguf new file mode 100644 index 0000000..7d393f4 --- /dev/null +++ b/Llama3-8B-ScaleQuest.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcec7e03101b2cd86bfb198e3e4909a377b8a655fdfddabd2f4a54f8ad668a67 +size 4484718784 diff --git a/Llama3-8B-ScaleQuest.Q2_K.gguf b/Llama3-8B-ScaleQuest.Q2_K.gguf new file mode 100644 index 0000000..d8076f7 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a03bfc21964b8740a4efe2098e7e7ade4123d8c8a2a432d8017b926fc6f0c6 +size 3179434176 diff --git a/Llama3-8B-ScaleQuest.Q3_K_L.gguf b/Llama3-8B-ScaleQuest.Q3_K_L.gguf new file mode 100644 index 0000000..7d199a8 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2dd74f54fa4f2aedcfc83cda65efb0c8204da5babb84b3134e738095c3583e6 +size 4322285760 diff --git a/Llama3-8B-ScaleQuest.Q3_K_M.gguf b/Llama3-8B-ScaleQuest.Q3_K_M.gguf new file mode 100644 index 0000000..880c6e5 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c95259f0b53aa0af5fd08cbbecf7bd13f6de5c7f1ff9200bc74178cdf02a3b +size 4019247296 diff --git a/Llama3-8B-ScaleQuest.Q3_K_S.gguf b/Llama3-8B-ScaleQuest.Q3_K_S.gguf new file mode 100644 index 0000000..17d91b7 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef380efc0f83d0cb3713359de66a8a0c74c1728d2a08da67f2810f8a8475dd2 +size 3664828608 diff --git a/Llama3-8B-ScaleQuest.Q4_K_M.gguf b/Llama3-8B-ScaleQuest.Q4_K_M.gguf new file mode 100644 index 0000000..1c031e6 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541adc5a53d624a218787304ca452e850ff84ad90716b91cb3042a9d625e1eb6 +size 4921098432 diff --git a/Llama3-8B-ScaleQuest.Q4_K_S.gguf b/Llama3-8B-ScaleQuest.Q4_K_S.gguf new file mode 100644 index 0000000..2d91869 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb907a71767c1d754adb800695b4967a6df5a498b899c6927ddb7d4fa5d47e0 +size 4693033152 diff --git a/Llama3-8B-ScaleQuest.Q5_K_M.gguf b/Llama3-8B-ScaleQuest.Q5_K_M.gguf new file mode 100644 index 0000000..aed713e --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66266c0ca59fb9580d91759d75e10966d2e0cc0b54526f54e3b10a53cc5ba86d +size 5733384384 diff --git a/Llama3-8B-ScaleQuest.Q5_K_S.gguf b/Llama3-8B-ScaleQuest.Q5_K_S.gguf new file mode 100644 index 0000000..8d592ab --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de3ab3bf3c6ddfcd61807db54ae72a392a7b3454adcf873c7119bee05c5e803 +size 5599690944 diff --git a/Llama3-8B-ScaleQuest.Q6_K.gguf b/Llama3-8B-ScaleQuest.Q6_K.gguf new file mode 100644 index 0000000..5df6386 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9373c23c5ae5f05b612b5826aa5cd45866032e372be6787e58065c120e9fa5d +size 6596438208 diff --git a/Llama3-8B-ScaleQuest.Q8_0.gguf b/Llama3-8B-ScaleQuest.Q8_0.gguf new file mode 100644 index 0000000..f9079f3 --- /dev/null +++ b/Llama3-8B-ScaleQuest.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ab498416931ea115449e17c4d824c6cc3c3e58ca222ec9b024b4fb3f8dcfbb +size 8541329600 diff --git a/Llama3-8B-ScaleQuest.f16.gguf b/Llama3-8B-ScaleQuest.f16.gguf new file mode 100644 index 0000000..7d20573 --- /dev/null +++ b/Llama3-8B-ScaleQuest.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d009c1f127bba1827d674b53fa494f354e48b990c53f3b622f546c15d102584 +size 16069941440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9fc65b4 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: dyyyyyyyy/Llama3-8B-ScaleQuest +datasets: +- dyyyyyyyy/ScaleQuest-Math +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/dyyyyyyyy/Llama3-8B-ScaleQuest + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-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/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-GGUF/resolve/main/Llama3-8B-ScaleQuest.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. + +