commit f021888f99ea68f72115b1292f4c57e3b3bbca1e Author: ModelHub XC Date: Fri Jun 26 20:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e28a938 --- /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 +LlamaXCoder-3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaXCoder-3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaXCoder-3.2-3B-Instruct.IQ4_XS.gguf b/LlamaXCoder-3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ebcd089 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c235119fd5e7e9972d5e49754d9475e18ff81a95a218500f99fc757d288cb665 +size 1840907456 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q2_K.gguf b/LlamaXCoder-3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..cc1b365 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c0d9c2024a7074d9a638c79d22054b9ea1fe8e863c8094bc9eb41f73685df1 +size 1363936448 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q3_K_L.gguf b/LlamaXCoder-3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..5f3f70e --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e360768cba847d82441e6c8945ec4dc9cd72e9368105e0461d099c31b241bb +size 1815348416 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q3_K_M.gguf b/LlamaXCoder-3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b21dae8 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9acf765a6855a521ca5ae7a86da0ddcc4114a9f844b2d585cc3230121b44bd8 +size 1687160000 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q3_K_S.gguf b/LlamaXCoder-3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..9536864 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef82f936753813c0d78a672c82fcf51341f60b1887706971c0e27dd270e80a2e +size 1542849728 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q4_K_M.gguf b/LlamaXCoder-3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..52d2a11 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76984150dbeba82c8c5303e48dca86e11bf8038674179b40d3343f406c266989 +size 2019378368 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q4_K_S.gguf b/LlamaXCoder-3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..d1f3e9c --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528648333544688ad1b8d459947728c1af400b296b81b7ac6500ae3d1d23b85c +size 1928201408 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q5_K_M.gguf b/LlamaXCoder-3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bd66c64 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cf362ce371eb844c80bf8707467346864c59bb72ae826db11b9d7b33c8dea9 +size 2322154688 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q5_K_S.gguf b/LlamaXCoder-3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..86441c0 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6367efc060e54882e712f192a208ad1ce8cf2a42d021023afae968a6bbd727bf +size 2269512896 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q6_K.gguf b/LlamaXCoder-3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..fdb2742 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab67dc80af5bc49fb4e3754d689c4ee5eed59710dd9024e7e6499fce4c83c244 +size 2643854528 diff --git a/LlamaXCoder-3.2-3B-Instruct.Q8_0.gguf b/LlamaXCoder-3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..e08c758 --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a004eb1f60a29aa923e153e499af1f894ea3846d52baec63f22a8c35f9eef2 +size 3421899968 diff --git a/LlamaXCoder-3.2-3B-Instruct.f16.gguf b/LlamaXCoder-3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..8d3ffdf --- /dev/null +++ b/LlamaXCoder-3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33153ae642fe9daf3f5ec0d51dfe5ed9354fe30255780b9e463d89001c723a94 +size 6433688768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e0ae499 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: motexture/LlamaXCoder-3.2-3B-Instruct +datasets: +- motexture/cData +language: +- en +- it +- es +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- coding +- coder +- model +- llama +--- +## About + + + + + + +static quants of https://huggingface.co/motexture/LlamaXCoder-3.2-3B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-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/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaXCoder-3.2-3B-Instruct-GGUF/resolve/main/LlamaXCoder-3.2-3B-Instruct.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. + +