commit 3a6d457caaca821a9c1afc34e202902f8b8120d1 Author: ModelHub XC Date: Sat Jul 18 02:55:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-2-3B-wame-slm4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..46c6285 --- /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-wame-slm4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-2-3B-wame-slm4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4feab34 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: wamegabe/llama-3-2-3B-wame-slm4 +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/wamegabe/llama-3-2-3B-wame-slm4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-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/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-2-3B-wame-slm4-GGUF/resolve/main/llama-3-2-3B-wame-slm4.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/llama-3-2-3B-wame-slm4.IQ4_XS.gguf b/llama-3-2-3B-wame-slm4.IQ4_XS.gguf new file mode 100644 index 0000000..f193fbc --- /dev/null +++ b/llama-3-2-3B-wame-slm4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bcd059bc2629ae66b020fa5a14b15723e3c5ea469144e40578553f70778498 +size 1840908064 diff --git a/llama-3-2-3B-wame-slm4.Q2_K.gguf b/llama-3-2-3B-wame-slm4.Q2_K.gguf new file mode 100644 index 0000000..f409b29 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1626080a524240870783832a8169a3018099270bd81f68dd54e13a20a7b23b40 +size 1363937056 diff --git a/llama-3-2-3B-wame-slm4.Q3_K_L.gguf b/llama-3-2-3B-wame-slm4.Q3_K_L.gguf new file mode 100644 index 0000000..e292c7b --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b28ccc5871e4c3cc3acd7ff08ad014d728908cca40456bb883e730bea8d130 +size 1815349024 diff --git a/llama-3-2-3B-wame-slm4.Q3_K_M.gguf b/llama-3-2-3B-wame-slm4.Q3_K_M.gguf new file mode 100644 index 0000000..bf34231 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62be274efa66cc48c4fd38371486ab74c15649604ca998a00059b5853231b5a +size 1687160608 diff --git a/llama-3-2-3B-wame-slm4.Q3_K_S.gguf b/llama-3-2-3B-wame-slm4.Q3_K_S.gguf new file mode 100644 index 0000000..d8ec335 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617841dd7f805e356054bb9e412bf5b787a2e20ccfb7f2261053ab79147ff318 +size 1542850336 diff --git a/llama-3-2-3B-wame-slm4.Q4_K_M.gguf b/llama-3-2-3B-wame-slm4.Q4_K_M.gguf new file mode 100644 index 0000000..7196959 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9746dfd03cdbbe21d49bb61bbe9e1600b2364ad20e3c3377d95c764a07193007 +size 2019378976 diff --git a/llama-3-2-3B-wame-slm4.Q4_K_S.gguf b/llama-3-2-3B-wame-slm4.Q4_K_S.gguf new file mode 100644 index 0000000..d838e00 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a7bc3236965802ec6a9d456f31a9d0cde872633e822a43b9c88935f5a9c341 +size 1928202016 diff --git a/llama-3-2-3B-wame-slm4.Q5_K_M.gguf b/llama-3-2-3B-wame-slm4.Q5_K_M.gguf new file mode 100644 index 0000000..cf28587 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc53b7da50d6c51e0d22ffe772987de1754338fbf5d510a3af8896a91dfa8f7c +size 2322155296 diff --git a/llama-3-2-3B-wame-slm4.Q5_K_S.gguf b/llama-3-2-3B-wame-slm4.Q5_K_S.gguf new file mode 100644 index 0000000..1f048de --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af7f2207133c5a1c32674bb05b5f1879a816ac9f9261358543dd6f3ee288807 +size 2269513504 diff --git a/llama-3-2-3B-wame-slm4.Q6_K.gguf b/llama-3-2-3B-wame-slm4.Q6_K.gguf new file mode 100644 index 0000000..56a4d7f --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc601accee1a3c7b2de8755a2837f1e5003a0b663894ca1b13c920fdfddbec4 +size 2643855136 diff --git a/llama-3-2-3B-wame-slm4.Q8_0.gguf b/llama-3-2-3B-wame-slm4.Q8_0.gguf new file mode 100644 index 0000000..f28b265 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e6fe7b0e607faa6ef4e9cc714aa4bc3f1e8d28ff24aba5f154c0610b33c96f +size 3421900576 diff --git a/llama-3-2-3B-wame-slm4.f16.gguf b/llama-3-2-3B-wame-slm4.f16.gguf new file mode 100644 index 0000000..c2bd612 --- /dev/null +++ b/llama-3-2-3B-wame-slm4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f42947d9d5fc18e7c46ca47568c0353d210f5c99593d7076b2bea0f7e0f2dc +size 6433689376