commit 790beb3d410a090bc20f46f6143503b71b0fee92 Author: ModelHub XC Date: Tue Jun 30 11:21:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce466ac --- /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 +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.IQ4_XS.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..82abcf5 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9d2e0d7ec453d70ee9b233e4b38dcb1f892e4962e526db24269d50fb77fe33 +size 1840907264 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q2_K.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q2_K.gguf new file mode 100644 index 0000000..efc0e93 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8060429a70eb65b78fc749c35e1642a1d8ce48a61a1a08e9303b5f0bcff91670 +size 1363936256 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_L.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..e50cf10 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7cce1b441948a1de7e34b398094f760216e3282cfc16eda0c03c97d11dbec4f +size 1815348224 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..a6c37c7 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77906e41afc6e2acc057aed7ef86349c4589a3237ef41b4467ca1f8578cde57c +size 1687159808 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..99cc26f --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5e73a9b20e7d8c8f0f12d094f465d273b88fd7a751276952161db9644bf08e +size 1542849536 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..73d1582 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b403733ab2472878163241c2041038a2f3d4db658de52194303dd50552ff83f +size 2019378176 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..e68b8af --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d6556369afcc3ac1c0b0b9d4a8f010789e0cb512fef5f7e6bb072dcce317024 +size 1928201216 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..b43797e --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc463f4ea9360572f2f34d8033e57a8a07546682999de9fbc473aae14344b70 +size 2322154496 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..13bf824 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f67bb89c19e2e380a6b436cba3db078d4f52966745032f7d460e02391028f35 +size 2269512704 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q6_K.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q6_K.gguf new file mode 100644 index 0000000..bd07db6 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e68f2a05cf8ff4376129e2408e0d8da86caeca720ecfe279dc74fce62b4a04 +size 2643854336 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q8_0.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q8_0.gguf new file mode 100644 index 0000000..6d4d317 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bda45e5478853a8b3e7f23fbc28a49baf03c19fe4892725d1e99dc6762096af +size 3421899776 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.f16.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.f16.gguf new file mode 100644 index 0000000..71a1e2c --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a696d879e18d97f8c34bea02e9e046da53bf85807968ca7ee99d91ac411c9d87 +size 6433688576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..518e7d1 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: DavidAU/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- reasoning +- thinking +- cot +- deepseek +- Llama 3.2 +- 128k context +- fine tune +- llama-3 +- llama-3.2 +--- +## About + + + + + + +static quants of https://huggingface.co/DavidAU/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-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/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.f16.gguf) | f16 | 6.5 | 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. + +