commit 8f28958561254af36df584fed04223fd6c3c4df2 Author: ModelHub XC Date: Tue May 26 07:47:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-MegaScience-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..51d7824 --- /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 +Llama3.1-8B-MegaScience.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-MegaScience.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-MegaScience.IQ4_XS.gguf b/Llama3.1-8B-MegaScience.IQ4_XS.gguf new file mode 100644 index 0000000..fc2a24b --- /dev/null +++ b/Llama3.1-8B-MegaScience.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1af74556813fa782b2eef880232faf392d8b38437521e5cb0d5e6c0b4820fe3 +size 4484364576 diff --git a/Llama3.1-8B-MegaScience.Q2_K.gguf b/Llama3.1-8B-MegaScience.Q2_K.gguf new file mode 100644 index 0000000..c773969 --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad562d388c8ea20b3f8a6d8866d47a5a58b243386fd28968285438c1f4752522 +size 3179133216 diff --git a/Llama3.1-8B-MegaScience.Q3_K_L.gguf b/Llama3.1-8B-MegaScience.Q3_K_L.gguf new file mode 100644 index 0000000..3e5eede --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f54575e6122fe29552ca79771e07d37b4a1cba93f482286535e682eeec69b7 +size 4321958176 diff --git a/Llama3.1-8B-MegaScience.Q3_K_M.gguf b/Llama3.1-8B-MegaScience.Q3_K_M.gguf new file mode 100644 index 0000000..eda9b08 --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f54875a9cc778c15fd81016830d1dd8c58f27dd6d45a3d897ddc1c71643767f +size 4018919712 diff --git a/Llama3.1-8B-MegaScience.Q3_K_S.gguf b/Llama3.1-8B-MegaScience.Q3_K_S.gguf new file mode 100644 index 0000000..0bba5ef --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c901ffc5fcb355081a7dd86f44cefb61cee5f8b7e36dd6abd39f87561f2321dc +size 3664501024 diff --git a/Llama3.1-8B-MegaScience.Q4_K_M.gguf b/Llama3.1-8B-MegaScience.Q4_K_M.gguf new file mode 100644 index 0000000..0d295ec --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de758765b4194279af270eb5d352e9aa5532fc756a6106be2d90c754bb64c575 +size 4920736032 diff --git a/Llama3.1-8B-MegaScience.Q4_K_S.gguf b/Llama3.1-8B-MegaScience.Q4_K_S.gguf new file mode 100644 index 0000000..e7a0ce0 --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf2a01cf13dd0c367722eda6448406abbfeef756f4aa207f9c3987f5cfc9e3c +size 4692670752 diff --git a/Llama3.1-8B-MegaScience.Q5_K_M.gguf b/Llama3.1-8B-MegaScience.Q5_K_M.gguf new file mode 100644 index 0000000..e5e2103 --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8102345ad95c508feac44aca828d5ad8cebada7d3f78b8fd667e37eca0962ea +size 5732989216 diff --git a/Llama3.1-8B-MegaScience.Q5_K_S.gguf b/Llama3.1-8B-MegaScience.Q5_K_S.gguf new file mode 100644 index 0000000..4e2bc40 --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5008e03840ea78b0437bd0feb22bb0c62b17cd5b44b1e088b75a728d0802550d +size 5599295776 diff --git a/Llama3.1-8B-MegaScience.Q6_K.gguf b/Llama3.1-8B-MegaScience.Q6_K.gguf new file mode 100644 index 0000000..70b403d --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2107f9dab500cdc3373c158dd5bc8bd3d80fa76c779c31121019159cabeb34c0 +size 6596008224 diff --git a/Llama3.1-8B-MegaScience.Q8_0.gguf b/Llama3.1-8B-MegaScience.Q8_0.gguf new file mode 100644 index 0000000..3a1e22d --- /dev/null +++ b/Llama3.1-8B-MegaScience.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0834d3be5b5b56fb81bb84a7280c93042590058d6f32895664b05655dae89b +size 8540772640 diff --git a/Llama3.1-8B-MegaScience.f16.gguf b/Llama3.1-8B-MegaScience.f16.gguf new file mode 100644 index 0000000..9ef0aeb --- /dev/null +++ b/Llama3.1-8B-MegaScience.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ce11b9b8133088d19b5a6afbac45e3cebcb00daee3a28f52da647aa7e4b453 +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c829f79 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: MegaScience/Llama3.1-8B-MegaScience +datasets: +- MegaScience/MegaScience +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- science +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MegaScience/Llama3.1-8B-MegaScience + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-MegaScience-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/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-MegaScience-GGUF/resolve/main/Llama3.1-8B-MegaScience.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. + +