commit 3d863cadbd25199b0ebdc5667583610461dd2f16 Author: ModelHub XC Date: Wed Jul 15 11:27:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c0162f3 --- /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_0.21_R1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Smarteaz_0.21_R1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.IQ4_XS.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.IQ4_XS.gguf new file mode 100644 index 0000000..c336150 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8744338c9a5945e7e9b34c71b8b8b4d3556a9e32c3091372eb8764c8851b0ad5 +size 4484409120 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q2_K.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q2_K.gguf new file mode 100644 index 0000000..a74a4a0 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:625dc81f26e103e394ba1a2cd5dcd8b6df87cd01475f61ece9b8258b77502049 +size 3179171104 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_L.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_L.gguf new file mode 100644 index 0000000..8241540 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b5fce43013c3a570903dc1d9ce7f3980feafe7350a40865fff54085238787a +size 4321999392 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_M.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_M.gguf new file mode 100644 index 0000000..91ae9ea --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff77c3b2d89008d4ee6c5486f33b55fedf58d44c6799cf6f2b22cdefca1f56a1 +size 4018960928 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_S.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_S.gguf new file mode 100644 index 0000000..2b73502 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb2b2ca0967055ed7908f1f07c4fbdd44a6b46bddf4a545860683b9e4f38a0d +size 3664542240 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_M.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_M.gguf new file mode 100644 index 0000000..8127928 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53760a70440aac1fe16765eea31de6eab61f36a35034635588d7ad74f7eb56ef +size 4920781600 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_S.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_S.gguf new file mode 100644 index 0000000..82c7358 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2665f8cb7de63f797a36dd21b18881a44f632c9cf83b19a2b3e94a358ddd72b +size 4692716320 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_M.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_M.gguf new file mode 100644 index 0000000..fce8575 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73721193162d55a576f44c46c11800823595a46352e0e021b3fdbaef403e8c00 +size 5733038880 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_S.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_S.gguf new file mode 100644 index 0000000..a7f4561 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2015ed7b2d529e3cfbc1e8df0b534b80ce4e5f9d09e77f780ac1f71a76cd22c +size 5599345440 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q6_K.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q6_K.gguf new file mode 100644 index 0000000..9110531 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97301b3f1a95bd0b2b128be3524ed7d6521839a982514c0e0eb0c41d7a830ba5 +size 6596062240 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.Q8_0.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.Q8_0.gguf new file mode 100644 index 0000000..e63b95a --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12671d869da545fea9f6217620033fd00120178bbde94474d5636916e35ae23e +size 8540842528 diff --git a/Llama_3.1_8b_Smarteaz_0.21_R1.f16.gguf b/Llama_3.1_8b_Smarteaz_0.21_R1.f16.gguf new file mode 100644 index 0000000..6f5c380 --- /dev/null +++ b/Llama_3.1_8b_Smarteaz_0.21_R1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f345567ecc63bb86aca1d87464f91f812c11138d8a430eb0c89b59f1f1755d28 +size 16069024288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3eaf2d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Smarteaz_0.21_R1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.1_8b_Smarteaz_0.21_R1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_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_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_R1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Smarteaz_0.21_R1-GGUF/resolve/main/Llama_3.1_8b_Smarteaz_0.21_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. + +