commit 19db707589a82a2db8210f1fbabad86a01b25b9e Author: ModelHub XC Date: Sun Jul 19 01:42:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-CLEAR-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d20eadb --- /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-CLEAR.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CLEAR.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-CLEAR.IQ4_XS.gguf b/Llama-3.2-3B-CLEAR.IQ4_XS.gguf new file mode 100644 index 0000000..41d9688 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f875bd7cfd69a4bf35ff07f1df5c4cd5fb8ec917f8bfb7eb2f74d1bd1bf08e4 +size 1840907296 diff --git a/Llama-3.2-3B-CLEAR.Q2_K.gguf b/Llama-3.2-3B-CLEAR.Q2_K.gguf new file mode 100644 index 0000000..cd03fb2 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76322207560f78c6673720bfed9a55c53e3acf21db13d31bc1c010d8bd066ec2 +size 1363936288 diff --git a/Llama-3.2-3B-CLEAR.Q3_K_L.gguf b/Llama-3.2-3B-CLEAR.Q3_K_L.gguf new file mode 100644 index 0000000..dbc7c26 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ed4940c84b81c02fdff248a672c3b3a0f1c5c36d5dc0bdf2549f2b72b7b06e +size 1815348256 diff --git a/Llama-3.2-3B-CLEAR.Q3_K_M.gguf b/Llama-3.2-3B-CLEAR.Q3_K_M.gguf new file mode 100644 index 0000000..3f08069 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a1e1be625da931ea4f15682928a9dcc0211973301527a621c04989ae5d435d +size 1687159840 diff --git a/Llama-3.2-3B-CLEAR.Q3_K_S.gguf b/Llama-3.2-3B-CLEAR.Q3_K_S.gguf new file mode 100644 index 0000000..ac946b4 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d3d4e04c9a9e0a9563fae5d6f5610599a5fcaa4ed61f6bb65bafe3366c6c33f +size 1542849568 diff --git a/Llama-3.2-3B-CLEAR.Q4_K_M.gguf b/Llama-3.2-3B-CLEAR.Q4_K_M.gguf new file mode 100644 index 0000000..987b983 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408fcf4dc8f43a651dba03f937e01991f602242f005965cfd2592ad874f6232e +size 2019378208 diff --git a/Llama-3.2-3B-CLEAR.Q4_K_S.gguf b/Llama-3.2-3B-CLEAR.Q4_K_S.gguf new file mode 100644 index 0000000..15d3041 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6b2afef2e1c1de26f8fedcaacb7db301720370819ff3aea6695f52df414875 +size 1928201248 diff --git a/Llama-3.2-3B-CLEAR.Q5_K_M.gguf b/Llama-3.2-3B-CLEAR.Q5_K_M.gguf new file mode 100644 index 0000000..a4a09f9 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3feab56d50e80d98bc9dec442b845600360dbc55044082f2905abe41c0bf9c07 +size 2322154528 diff --git a/Llama-3.2-3B-CLEAR.Q5_K_S.gguf b/Llama-3.2-3B-CLEAR.Q5_K_S.gguf new file mode 100644 index 0000000..7605f5e --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c05afed209313d58b915c243c88310982be4ba6dc4b31bfb19fcb23f5214918 +size 2269512736 diff --git a/Llama-3.2-3B-CLEAR.Q6_K.gguf b/Llama-3.2-3B-CLEAR.Q6_K.gguf new file mode 100644 index 0000000..0ac96dd --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3dd3c6a76f734daf35b6454eb61615eb43cab027ffa0ba73ec6deecd20bed2e +size 2643854368 diff --git a/Llama-3.2-3B-CLEAR.Q8_0.gguf b/Llama-3.2-3B-CLEAR.Q8_0.gguf new file mode 100644 index 0000000..4ac536b --- /dev/null +++ b/Llama-3.2-3B-CLEAR.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42c95c5ae7084ddbb812eeb51c0db7075fa612e4c0d5467d7f08d3a366195148 +size 3421899808 diff --git a/Llama-3.2-3B-CLEAR.f16.gguf b/Llama-3.2-3B-CLEAR.f16.gguf new file mode 100644 index 0000000..5540306 --- /dev/null +++ b/Llama-3.2-3B-CLEAR.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9085410cf60bf703cf01ec29a1f325e29bbe68966bbfd3bfcf7a6792d11828a2 +size 6433688608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..28dcb28 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: oscarwu/Llama-3.2-3B-CLEAR +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- climate-policy +- query-interpretation +- lora +--- +## About + + + + + + +static quants of https://huggingface.co/oscarwu/Llama-3.2-3B-CLEAR + + +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-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CLEAR-GGUF/resolve/main/Llama-3.2-3B-CLEAR.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. + +