commit e5b0f5a5db0bd1313e5b21be4ca4c22e2e49a87c Author: ModelHub XC Date: Thu Oct 22 01:36:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ReWiz-Llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3691b4 --- /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 +ReWiz-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9d0979 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: theprint/ReWiz-Llama-3.2-3B +datasets: +- KingNish/reasoning-base-20k +- arcee-ai/EvolKit-20k +- cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +- theprint +- ReWiz +--- +## About + + + + + + +static quants of https://huggingface.co/theprint/ReWiz-Llama-3.2-3B + + +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/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-GGUF/resolve/main/ReWiz-Llama-3.2-3B.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. + + diff --git a/ReWiz-Llama-3.2-3B.IQ4_XS.gguf b/ReWiz-Llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..964dea5 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f497e4dc3ba5c2b0fd267cd998fda38ecc42c810de841dc438fe25e1e662932 +size 1840908160 diff --git a/ReWiz-Llama-3.2-3B.Q2_K.gguf b/ReWiz-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..5c50c61 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a4c1e61aef74982b221fbcaa02c2cf0196ef05387b05419903346a08b9ac4f +size 1363937152 diff --git a/ReWiz-Llama-3.2-3B.Q3_K_L.gguf b/ReWiz-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..149cae8 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb344a14ac1fcd41b803d5cc255df85c7021cbbb3dcde9f857a289b9860ff1c +size 1815349120 diff --git a/ReWiz-Llama-3.2-3B.Q3_K_M.gguf b/ReWiz-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..f646d70 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f616821eb5e7e64f7b0d872e41416b32fabcd8dc7e1076bb895a135ce1a109 +size 1687160704 diff --git a/ReWiz-Llama-3.2-3B.Q3_K_S.gguf b/ReWiz-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..936057d --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7af05fbb19a7b9a0b32122880f0c75236ed2fbb5e9c2bf10c9489a806f554c +size 1542850432 diff --git a/ReWiz-Llama-3.2-3B.Q4_K_M.gguf b/ReWiz-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..3ae0ad0 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9120f17233c172749634c8cce9f549ca0e61c8cbf4ac9bdf334168801617a15b +size 2019379072 diff --git a/ReWiz-Llama-3.2-3B.Q4_K_S.gguf b/ReWiz-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..95192e1 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04cdeb18c6d2a74d64a1ddf74fc6fc952aa48409420d119446671129288de130 +size 1928202112 diff --git a/ReWiz-Llama-3.2-3B.Q5_K_M.gguf b/ReWiz-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..3a96823 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493cd0c5dc3938c6a2eef464e354017267fe7ad76ec1d3c755b2c9f557a08ce1 +size 2322155392 diff --git a/ReWiz-Llama-3.2-3B.Q5_K_S.gguf b/ReWiz-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..ea127b5 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8db9931785fca56fc96d06c2ae30a48059cbbf828e0b5a5fa00695120f25cc7 +size 2269513600 diff --git a/ReWiz-Llama-3.2-3B.Q6_K.gguf b/ReWiz-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..4d2efbe --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a940cd9e355246e11cd09f0d0ed83f413375d4d973ee54fca403e0502be32 +size 2643855232 diff --git a/ReWiz-Llama-3.2-3B.Q8_0.gguf b/ReWiz-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..d8c3d22 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051f355ff7123cfc0b368cc53e364fee1de3538dafab77c954bb2fbdd9e4701d +size 3421900672 diff --git a/ReWiz-Llama-3.2-3B.f16.gguf b/ReWiz-Llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..9224441 --- /dev/null +++ b/ReWiz-Llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44081dfd79b9b0bf518b2716739357a37d7c94c84ef92d54d31f16462bd4767d +size 6433689472