commit 4be4ea988b5a48dd47d0b7b80cba233d04180475 Author: ModelHub XC Date: Tue Sep 29 09:27:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2_3B_Reasoning_V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86d8702 --- /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 +Llama3.2_3B_Reasoning_V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2_3B_Reasoning_V2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2_3B_Reasoning_V2.IQ4_XS.gguf b/Llama3.2_3B_Reasoning_V2.IQ4_XS.gguf new file mode 100644 index 0000000..98ce4be --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0777a049c71a6233526abeaac15e7b1995f6cbd1e5d00885351ede981f64f5c +size 1840908128 diff --git a/Llama3.2_3B_Reasoning_V2.Q2_K.gguf b/Llama3.2_3B_Reasoning_V2.Q2_K.gguf new file mode 100644 index 0000000..8501079 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecbaabc9569f357285b9494defbb354ee415d7adf005a52ed94edf2abc687638 +size 1363937120 diff --git a/Llama3.2_3B_Reasoning_V2.Q3_K_L.gguf b/Llama3.2_3B_Reasoning_V2.Q3_K_L.gguf new file mode 100644 index 0000000..f3a43e9 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611d087dd7746f1de1eedba3a5f7556de2d6af4680dbee4ed6a5233efa8d568d +size 1815349088 diff --git a/Llama3.2_3B_Reasoning_V2.Q3_K_M.gguf b/Llama3.2_3B_Reasoning_V2.Q3_K_M.gguf new file mode 100644 index 0000000..a5fab76 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad1947760cd8a42f2ab1cba6742d291bdd6046f8887ac7b2331f1517493c3b8 +size 1687160672 diff --git a/Llama3.2_3B_Reasoning_V2.Q3_K_S.gguf b/Llama3.2_3B_Reasoning_V2.Q3_K_S.gguf new file mode 100644 index 0000000..05c6435 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e638561bfd91a57ae3cc1aa74adb7d5667c9509056a57bdd175533f9fbb0b480 +size 1542850400 diff --git a/Llama3.2_3B_Reasoning_V2.Q4_K_M.gguf b/Llama3.2_3B_Reasoning_V2.Q4_K_M.gguf new file mode 100644 index 0000000..52c70d7 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384fed815e0740894cf5fc0a51f45a37c4fadb0f2bda5710f380182c8577d41b +size 2019379040 diff --git a/Llama3.2_3B_Reasoning_V2.Q4_K_S.gguf b/Llama3.2_3B_Reasoning_V2.Q4_K_S.gguf new file mode 100644 index 0000000..24c0be9 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22a099bac7a1eb567209b36608f95437d49d566a8b073978f27347bd8e3de5ab +size 1928202080 diff --git a/Llama3.2_3B_Reasoning_V2.Q5_K_M.gguf b/Llama3.2_3B_Reasoning_V2.Q5_K_M.gguf new file mode 100644 index 0000000..5a600ec --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a0f8cb4f71066a866a7de97a04004ba02efcd6a785991822fca0a7405f022c +size 2322155360 diff --git a/Llama3.2_3B_Reasoning_V2.Q5_K_S.gguf b/Llama3.2_3B_Reasoning_V2.Q5_K_S.gguf new file mode 100644 index 0000000..a054be2 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7512e1c1736f353a7d636c25578b5c3c1334a5e98e1bd66028838dd88750c45e +size 2269513568 diff --git a/Llama3.2_3B_Reasoning_V2.Q6_K.gguf b/Llama3.2_3B_Reasoning_V2.Q6_K.gguf new file mode 100644 index 0000000..33528dc --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e3d0107e4b81eeec0f7c2503b463a3f4dc83cf2d2b475ebc0536444190eeab +size 2643855200 diff --git a/Llama3.2_3B_Reasoning_V2.Q8_0.gguf b/Llama3.2_3B_Reasoning_V2.Q8_0.gguf new file mode 100644 index 0000000..60e1696 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6b2b9858a4427b143074516fb0fa2e96baee2ed2bed2d6817b2087003c5a9e +size 3421900640 diff --git a/Llama3.2_3B_Reasoning_V2.f16.gguf b/Llama3.2_3B_Reasoning_V2.f16.gguf new file mode 100644 index 0000000..a565bb5 --- /dev/null +++ b/Llama3.2_3B_Reasoning_V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc85791437485e4159f9bed1fe76e63d93e1a9ca05b5b8996b6909d869ddc37 +size 6433689440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..14b5ce5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Aditya0619/Llama3.2_3B_Reasoning_V2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Aditya0619/Llama3.2_3B_Reasoning_V2 + + +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/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2_3B_Reasoning_V2-GGUF/resolve/main/Llama3.2_3B_Reasoning_V2.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. + +