commit ba91c574320367f278daba0cb835b61a31c9d69d Author: ModelHub XC Date: Thu Jun 25 01:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86c0c16 --- /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 +Llama_3.1_8b_Smarteaz_0.2_R1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.2_R1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.IQ4_XS.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.IQ4_XS.gguf new file mode 100644 index 0000000..ec06938 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee583951aacffe78d49c556912a8cefa0554d2f66fe8675fe3ed45d22d7e7569 +size 4484366400 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q2_K.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q2_K.gguf new file mode 100644 index 0000000..3f5a558 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531c141cc1e1edefb8e927ee92c6e372666dfdc433037913ad891ed5b0ed5c0d +size 3179135040 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_L.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_L.gguf new file mode 100644 index 0000000..99767b4 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5005f8bb35e37aee65216444e64d0ee4cc3eff8db0a9b41b77a6f1d6bf4b1f03 +size 4321960000 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_M.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_M.gguf new file mode 100644 index 0000000..1fbff60 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a22ccd0942adc40f2cc657765be8b35d25fa309dab4d93983672540fe36dc144 +size 4018921536 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_S.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_S.gguf new file mode 100644 index 0000000..aaf3545 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf5d5c4e59bf3ea01dd176696d665c49a256472be45dfd51064174a911e6821 +size 3664502848 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_M.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_M.gguf new file mode 100644 index 0000000..2848ff7 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e389272fb7969afe3954310f425adf6b6ed06bd34c240dd051b63e57843079be +size 4920737856 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_S.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_S.gguf new file mode 100644 index 0000000..d1b05c4 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e913bfa8e508c2562faf731b15bd0c33bf2231fb280a7677fca64c4d48d7b11e +size 4692672576 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_M.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_M.gguf new file mode 100644 index 0000000..f7747bb --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d9721d0e19b125c44e65c796988cba8803892e74b45aa19a99aa62b49f501c +size 5732991040 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_S.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_S.gguf new file mode 100644 index 0000000..0ac8568 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8288993015081abcd40e9ba539f789ce036f95dea0dd637b1b99e71de0d0c8fa +size 5599297600 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q6_K.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q6_K.gguf new file mode 100644 index 0000000..d93e808 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:980052a1cf30affd6cf71546e11ef38b288114aa4fe886fcbcc50f2a193b4f21 +size 6596010048 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.Q8_0.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.Q8_0.gguf new file mode 100644 index 0000000..c11136e --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f4c9ef7ef8aacbadf0f4c0644dae2ab909b0b049f26ad816e0dabcd04d74b9 +size 8540774464 diff --git a/Llama_3.1_8b_Smarteaz_0.2_R1.f16.gguf b/Llama_3.1_8b_Smarteaz_0.2_R1.f16.gguf new file mode 100644 index 0000000..f9f28e9 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.2_R1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c182a1c1ca55168f6a365d22b31a08f04f03d79d29040a1189acb63b95096d +size 16068894784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec6f6ea --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Smarteaz_0.2_R1 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.1_8b_Smarteaz_0.2_R1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama_3.1_8b_Smarteaz_0.2_R1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-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/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.2_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.2_R1.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. + +