commit 42f94af736a5e5df25dbb47517d7d939e58590cc Author: ModelHub XC Date: Thu Jul 16 16:14:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd5e934 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-fix-config.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReWiz-Llama-3.2-3B-fix-config.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..515dea6 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: djuna/ReWiz-Llama-3.2-3B-fix-config +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/djuna/ReWiz-Llama-3.2-3B-fix-config + + +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-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF/resolve/main/ReWiz-Llama-3.2-3B-fix-config.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-fix-config.IQ4_XS.gguf b/ReWiz-Llama-3.2-3B-fix-config.IQ4_XS.gguf new file mode 100644 index 0000000..3400e5d --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8113b820507931eafcb2ed6b11af4e4fbc750ac7de9632b3e22ed9bee8e4554 +size 1840908192 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q2_K.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q2_K.gguf new file mode 100644 index 0000000..e64b601 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0414ba0f36e38a7306a5e5fefe7d974783875a09f599d29230ca1a0d4f0f01 +size 1363937184 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q3_K_L.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q3_K_L.gguf new file mode 100644 index 0000000..69abac3 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba349ca9b46afec7ad75d0b626bef4e31f6c320acc6de05a951e5772902e5a8 +size 1815349152 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q3_K_M.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q3_K_M.gguf new file mode 100644 index 0000000..f6e7589 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfb2f2cd464f1c847cca3c2f6e613ecdf7a27ecb68f2f5ec5d44e1138dfe641f +size 1687160736 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q3_K_S.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q3_K_S.gguf new file mode 100644 index 0000000..b20b440 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a42688fc4fd94a91e513655bf3cf91d29babe0c0f329ca25b954ee9be76f1a5 +size 1542850464 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q4_K_M.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q4_K_M.gguf new file mode 100644 index 0000000..05d2010 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84bd0b1ac9a96d4d2c8dd96aa9036ec48de74b5e6f5c119f1da50ae3e55c6758 +size 2019379104 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q4_K_S.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q4_K_S.gguf new file mode 100644 index 0000000..cb0e71f --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0005e083c3670b75a26f532d748e6755b60ab6e20fa7bc874a8f1f774a0d9b16 +size 1928202144 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q5_K_M.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q5_K_M.gguf new file mode 100644 index 0000000..9951b1e --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7575a8f5d002ac4fda3510b21919ec94bdc256ecf9fa446859879af0375f87 +size 2322155424 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q5_K_S.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q5_K_S.gguf new file mode 100644 index 0000000..58ea13a --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a837f45656218c958e092cc1dd3cef5a49f29c647ad4ac096603194e69d0353b +size 2269513632 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q6_K.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q6_K.gguf new file mode 100644 index 0000000..0b5d2df --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c781ff27b7d73518bf7bf7ea1a010e89f68ff16cb9bf39ba327617825b78182 +size 2643855264 diff --git a/ReWiz-Llama-3.2-3B-fix-config.Q8_0.gguf b/ReWiz-Llama-3.2-3B-fix-config.Q8_0.gguf new file mode 100644 index 0000000..87f26f3 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b4b1743f1223da3d157e0346ef2e671fd9ddd5113ddb3b3ba9df77cb32595c +size 3421900704 diff --git a/ReWiz-Llama-3.2-3B-fix-config.f16.gguf b/ReWiz-Llama-3.2-3B-fix-config.f16.gguf new file mode 100644 index 0000000..9aaea39 --- /dev/null +++ b/ReWiz-Llama-3.2-3B-fix-config.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e265ce167ef1acbe253d1f1d7974bbb6503fbecbe26ec1465118e13321c280 +size 6433689504