commit b8d17bd4b885619c41a1847f2bc8f7a584364219 Author: ModelHub XC Date: Mon Jun 15 18:26:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sad-Llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3b011f6 --- /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 +Sad-Llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sad-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sad-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..6cd3e16 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: SaisExperiments/Sad-Llama-3.2-3B +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SaisExperiments/Sad-Llama-3.2-3B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-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/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Sad-Llama-3.2-3B-GGUF/resolve/main/Sad-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/Sad-Llama-3.2-3B.IQ4_XS.gguf b/Sad-Llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..99cc5f2 --- /dev/null +++ b/Sad-Llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f523f70557b7efef69f32d6de5d6d5a2ac7ac20e0fb18762eceb71eb884000 +size 1840907072 diff --git a/Sad-Llama-3.2-3B.Q2_K.gguf b/Sad-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..bf6a7dd --- /dev/null +++ b/Sad-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1625b6c95435e616f6899d641b60214c978bf6445314dd5ac819ce2dbf34de +size 1363936064 diff --git a/Sad-Llama-3.2-3B.Q3_K_L.gguf b/Sad-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..f6c03c6 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf12a3c61d7d5b519c087085723eefc2b5105c6b90cd725a80d079f94e206c96 +size 1815348032 diff --git a/Sad-Llama-3.2-3B.Q3_K_M.gguf b/Sad-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..e20df8f --- /dev/null +++ b/Sad-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd35d1895976158d325674aa92e476bd620acfdf82b031443ba442d5f865519 +size 1687159616 diff --git a/Sad-Llama-3.2-3B.Q3_K_S.gguf b/Sad-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..8720861 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2205e7053aa9a2fc8a1f25d5254dc7db39d65856c715265b6ae44521cab384 +size 1542849344 diff --git a/Sad-Llama-3.2-3B.Q4_K_M.gguf b/Sad-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..c1f59f5 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adbac1e2526929ef18a91b325bbbf760ec333e3f311fc1b028d1557b1467457e +size 2019377984 diff --git a/Sad-Llama-3.2-3B.Q4_K_S.gguf b/Sad-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..92f1189 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a59cbfe9d2ac4117c9da882cc1bbe1ceae8a64acb5da0426196c7d4cea0484 +size 1928201024 diff --git a/Sad-Llama-3.2-3B.Q5_K_M.gguf b/Sad-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..e8e4505 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70abeb2d98ae89b6d6b967dd5251d7056348063183d96d7f9a9cd65d011d176f +size 2322154304 diff --git a/Sad-Llama-3.2-3B.Q5_K_S.gguf b/Sad-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..960c232 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e71b0f0ac834420058826f98d8f7a08810e3791a69d7c4e982cdbc473638f16 +size 2269512512 diff --git a/Sad-Llama-3.2-3B.Q6_K.gguf b/Sad-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..672f163 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b26a588be59afe628b06b8ee8cf776ced8ab3673f763955d6641314df3d5c8 +size 2643854144 diff --git a/Sad-Llama-3.2-3B.Q8_0.gguf b/Sad-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..89b1954 --- /dev/null +++ b/Sad-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658c4da9b90ff881ba7bbcc481b20b3bc1214cd86f7242de7a9ce01889ae0636 +size 3421899584 diff --git a/Sad-Llama-3.2-3B.f16.gguf b/Sad-Llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..a7bd1d1 --- /dev/null +++ b/Sad-Llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a28e25e1c6da4fa834724ecd398bfe19a7b970d9ad4264d17745e451f39168c +size 6433688384