commit 860e1f1f476d62e6f270a07baf0830dd8f0e8c48 Author: ModelHub XC Date: Sat Jun 13 18:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..26e5a2f --- /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-3.2-3B-Reasoning-Time.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Reasoning-Time.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Reasoning-Time.IQ4_XS.gguf b/Llama-3.2-3B-Reasoning-Time.IQ4_XS.gguf new file mode 100644 index 0000000..6d30e98 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151a2ef688402ce8fadee0c343b7b1aa0ee9bab9ac664f7a2855e8f060835781 +size 1840904160 diff --git a/Llama-3.2-3B-Reasoning-Time.Q2_K.gguf b/Llama-3.2-3B-Reasoning-Time.Q2_K.gguf new file mode 100644 index 0000000..10c7103 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8d2fad01343bc48f10a40ec356051d552c289955735cb4a5914f51c13eb74a +size 1363933152 diff --git a/Llama-3.2-3B-Reasoning-Time.Q3_K_L.gguf b/Llama-3.2-3B-Reasoning-Time.Q3_K_L.gguf new file mode 100644 index 0000000..db21ca2 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978013e7cb1186ad928ea035eea3f65aa2fdb2ab109374b76c5b011f5c59523e +size 1815345120 diff --git a/Llama-3.2-3B-Reasoning-Time.Q3_K_M.gguf b/Llama-3.2-3B-Reasoning-Time.Q3_K_M.gguf new file mode 100644 index 0000000..1b810e5 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37ddf2b797ffc1b1ab01692d41dfea815f1509e0b061111f134b7d8a6deec30 +size 1687156704 diff --git a/Llama-3.2-3B-Reasoning-Time.Q3_K_S.gguf b/Llama-3.2-3B-Reasoning-Time.Q3_K_S.gguf new file mode 100644 index 0000000..d7ae99d --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c37e767961ebd69e05ba2fd501bf6929d6943bb5589111345a69602923ce28f +size 1542846432 diff --git a/Llama-3.2-3B-Reasoning-Time.Q4_K_M.gguf b/Llama-3.2-3B-Reasoning-Time.Q4_K_M.gguf new file mode 100644 index 0000000..7e84095 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b10e1a5c6e27f6d8cf08c3472af2b15a9f63ebf8385eedfe8615f85116c73f +size 2019375072 diff --git a/Llama-3.2-3B-Reasoning-Time.Q4_K_S.gguf b/Llama-3.2-3B-Reasoning-Time.Q4_K_S.gguf new file mode 100644 index 0000000..fa77726 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ec22dafcddd4a881796b12a071fd5f89eea48c948568c04aef6eea8419670e +size 1928198112 diff --git a/Llama-3.2-3B-Reasoning-Time.Q5_K_M.gguf b/Llama-3.2-3B-Reasoning-Time.Q5_K_M.gguf new file mode 100644 index 0000000..6a61a8f --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff504fee32a0d3d5fb5dfc6bd0a172a34fe67b99c1f0ea67fa95f67040bc1af +size 2322151392 diff --git a/Llama-3.2-3B-Reasoning-Time.Q5_K_S.gguf b/Llama-3.2-3B-Reasoning-Time.Q5_K_S.gguf new file mode 100644 index 0000000..c63f865 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf627412a7db6e926a8301fc1db9fba6eb8adf1d397d0d4ac5e3485b4685104 +size 2269509600 diff --git a/Llama-3.2-3B-Reasoning-Time.Q6_K.gguf b/Llama-3.2-3B-Reasoning-Time.Q6_K.gguf new file mode 100644 index 0000000..da7bab1 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acecaeca2645f17bc34f6d48dfb84e726b260c8f30ce053674b9835404bafc6f +size 2643851232 diff --git a/Llama-3.2-3B-Reasoning-Time.Q8_0.gguf b/Llama-3.2-3B-Reasoning-Time.Q8_0.gguf new file mode 100644 index 0000000..6eba841 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6d60ea2a8b2287b9452cf1592c27a6cd92013c48e5cd025e89bee597169193 +size 3421896672 diff --git a/Llama-3.2-3B-Reasoning-Time.f16.gguf b/Llama-3.2-3B-Reasoning-Time.f16.gguf new file mode 100644 index 0000000..8da5cb5 --- /dev/null +++ b/Llama-3.2-3B-Reasoning-Time.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b8a553bda953d6bfed616ad5e252bcc7b5ca14bf494695307f2531e8a0e818 +size 6433685472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..04e85cc --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Lyte/Llama-3.2-3B-Reasoning-Time +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/Lyte/Llama-3.2-3B-Reasoning-Time + + +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/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Reasoning-Time-GGUF/resolve/main/Llama-3.2-3B-Reasoning-Time.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. + +