commit d517b5d2eb52c901b8170e4307b4606819c5102e Author: ModelHub XC Date: Sun Aug 23 20:39:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QCompiler-Llama3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5920213 --- /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 +QCompiler-Llama3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QCompiler-Llama3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QCompiler-Llama3.2-3B.IQ4_XS.gguf b/QCompiler-Llama3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..f0882a2 --- /dev/null +++ b/QCompiler-Llama3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2885b94535dc0f55bc5babf33fbce938274d05c9f2c766dd7f1c6e04d100a0 +size 1840906976 diff --git a/QCompiler-Llama3.2-3B.Q2_K.gguf b/QCompiler-Llama3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..b2a20cf --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8dcc8e5a6fd40d70db4731ef2490d0cbc22576d7f48ddc2698220a0b4d71bb4 +size 1363935968 diff --git a/QCompiler-Llama3.2-3B.Q3_K_L.gguf b/QCompiler-Llama3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..c88eee2 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79248778d64a3a14ee1091064d2baf3c1f9320cb5885a7816db00bc1f6f5bf20 +size 1815347936 diff --git a/QCompiler-Llama3.2-3B.Q3_K_M.gguf b/QCompiler-Llama3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..7246e23 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d16c4f0a6ea02a37d578ded0c7f967f6cda52d2d9297e3f23256750dd294f6fc +size 1687159520 diff --git a/QCompiler-Llama3.2-3B.Q3_K_S.gguf b/QCompiler-Llama3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..2f08fe6 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d3ccadea39622dde2c59629ce62769cfa191502104e510decc47a549c50d5a +size 1542849248 diff --git a/QCompiler-Llama3.2-3B.Q4_K_M.gguf b/QCompiler-Llama3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..bc45086 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaccd8b97e6abf5945b335fd8d980829a880b8d5871d00f1af98b92cc24845b6 +size 2019377888 diff --git a/QCompiler-Llama3.2-3B.Q4_K_S.gguf b/QCompiler-Llama3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..5898fb5 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1529d5d08d9cd06e7e806a7a9edcdb09be7e4fa7573f548b983a1314a0a8a97c +size 1928200928 diff --git a/QCompiler-Llama3.2-3B.Q5_K_M.gguf b/QCompiler-Llama3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..5777d08 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d3a8c1d5707eb51d0946c78836074b203650083807aea53c2a955d3518971e +size 2322154208 diff --git a/QCompiler-Llama3.2-3B.Q5_K_S.gguf b/QCompiler-Llama3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..560bb0a --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54720b7ee3963598b679fffce7d1d46acb13216b3b1fdd4bd7f7acfa36bfb804 +size 2269512416 diff --git a/QCompiler-Llama3.2-3B.Q6_K.gguf b/QCompiler-Llama3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..cc35877 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36706fcac02e7739ed59a831cc51bef3f52f52c7014fd6e87362c210074ae604 +size 2643854048 diff --git a/QCompiler-Llama3.2-3B.Q8_0.gguf b/QCompiler-Llama3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..128eb60 --- /dev/null +++ b/QCompiler-Llama3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ca7561beaf426c960ee6f8108a80c49e16d620bd62acbec403aed5f9358513 +size 3421899488 diff --git a/QCompiler-Llama3.2-3B.f16.gguf b/QCompiler-Llama3.2-3B.f16.gguf new file mode 100644 index 0000000..7023092 --- /dev/null +++ b/QCompiler-Llama3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0274d00eb4d11b7cbb4f1b8b5a2317ee4c341c814d156ef811f22ba1b6372a5 +size 6433688288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01e988a --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: KeriaZhang/QCompiler-Llama3.2-3B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/KeriaZhang/QCompiler-Llama3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QCompiler-Llama3.2-3B-GGUF).*** + +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/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QCompiler-Llama3.2-3B-GGUF/resolve/main/QCompiler-Llama3.2-3B.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. + +