commit 6ac8e1122f8137d2462e8fb0b25451a23afd403b Author: ModelHub XC Date: Mon Jun 15 20:38:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-r1-reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..799f7af --- /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-r1-reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-r1-reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d055ba2 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: fuland539/llama3.1-r1-reasoning +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/fuland539/llama3.1-r1-reasoning + + +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-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-r1-reasoning-GGUF/resolve/main/llama3.1-r1-reasoning.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. + + diff --git a/llama3.1-r1-reasoning.IQ4_XS.gguf b/llama3.1-r1-reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..6c75248 --- /dev/null +++ b/llama3.1-r1-reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1775c512a191689ea538bc528ff4e0543dfc8e743442a7ce6baae7017f424f5 +size 4484367712 diff --git a/llama3.1-r1-reasoning.Q2_K.gguf b/llama3.1-r1-reasoning.Q2_K.gguf new file mode 100644 index 0000000..8c65499 --- /dev/null +++ b/llama3.1-r1-reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04feefb66594379a821f9076f6b798df7f216b3f0696202ed6ac8d6d287475a4 +size 3179136352 diff --git a/llama3.1-r1-reasoning.Q3_K_L.gguf b/llama3.1-r1-reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..96e6923 --- /dev/null +++ b/llama3.1-r1-reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786a4b5cecd86d7b3a0309b60f5b579a1c106b9b7bd427575870437ef0a763f5 +size 4321961312 diff --git a/llama3.1-r1-reasoning.Q3_K_M.gguf b/llama3.1-r1-reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..68ec5ca --- /dev/null +++ b/llama3.1-r1-reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f7781ed05a9dc93425524827c81ce0d7d132f4233e573904a9c33e58eabf13 +size 4018922848 diff --git a/llama3.1-r1-reasoning.Q3_K_S.gguf b/llama3.1-r1-reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..562f1aa --- /dev/null +++ b/llama3.1-r1-reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863c6ef2cdea35bd9a516a328b665642d19ff3bb05098cedf0937080757bd748 +size 3664504160 diff --git a/llama3.1-r1-reasoning.Q4_K_M.gguf b/llama3.1-r1-reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..c66a5fa --- /dev/null +++ b/llama3.1-r1-reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:977e0407e4af3fe7aadadae4f8ea9a9c7493faca87940f3e27f04259df9d6912 +size 4920739168 diff --git a/llama3.1-r1-reasoning.Q4_K_S.gguf b/llama3.1-r1-reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..7d1bb93 --- /dev/null +++ b/llama3.1-r1-reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a2f83dd53657c3f1921ad960c74ffad5b623d65b07f7d2eaa4fb628c77f99b6 +size 4692673888 diff --git a/llama3.1-r1-reasoning.Q5_K_M.gguf b/llama3.1-r1-reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..717471d --- /dev/null +++ b/llama3.1-r1-reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302431eb09e849eaee734d2199b16b2e96f0b1c3839f21806cebe17faeb7f9c8 +size 5732992352 diff --git a/llama3.1-r1-reasoning.Q5_K_S.gguf b/llama3.1-r1-reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..150a8f1 --- /dev/null +++ b/llama3.1-r1-reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb936197e9262904d46eeb36ba7ee4b7cb94e8241852536a5515b587b6024ba +size 5599298912 diff --git a/llama3.1-r1-reasoning.Q6_K.gguf b/llama3.1-r1-reasoning.Q6_K.gguf new file mode 100644 index 0000000..e568736 --- /dev/null +++ b/llama3.1-r1-reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9c958e9dbb4e47084fc95e9e19e8bf8cc9cb5380c61fedde3bbddff9ce001d +size 6596011360 diff --git a/llama3.1-r1-reasoning.Q8_0.gguf b/llama3.1-r1-reasoning.Q8_0.gguf new file mode 100644 index 0000000..b3a880b --- /dev/null +++ b/llama3.1-r1-reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43315d54109fbca67235b94683da75ae9874def1413faf9da6826b5e1a71c1c6 +size 8540775776 diff --git a/llama3.1-r1-reasoning.f16.gguf b/llama3.1-r1-reasoning.f16.gguf new file mode 100644 index 0000000..7ab94b1 --- /dev/null +++ b/llama3.1-r1-reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cabce5bab0b4a6addbecddc27d99592f2531d121ece22fd52fd152cc1029edf9 +size 16068896096