commit 6e9f833c2208be29354c102c0fd1b3a0e32da685 Author: ModelHub XC Date: Fri Jun 5 17:20:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Distilled-Qwen-3B-Coder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b1edc3b --- /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 +Distilled-Qwen-3B-Coder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Distilled-Qwen-3B-Coder.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Distilled-Qwen-3B-Coder.IQ4_XS.gguf b/Distilled-Qwen-3B-Coder.IQ4_XS.gguf new file mode 100644 index 0000000..964d0dc --- /dev/null +++ b/Distilled-Qwen-3B-Coder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1720abdcfee52f91b246011bc3c9794bb36fe4f437a89ced4dae2663d505eea7 +size 1753185568 diff --git a/Distilled-Qwen-3B-Coder.Q2_K.gguf b/Distilled-Qwen-3B-Coder.Q2_K.gguf new file mode 100644 index 0000000..25733cc --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f373716ae81e74eebd5074417a71d329e001b023195838514e37143adb8a8d +size 1274756384 diff --git a/Distilled-Qwen-3B-Coder.Q3_K_L.gguf b/Distilled-Qwen-3B-Coder.Q3_K_L.gguf new file mode 100644 index 0000000..a8fabfb --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b67070aaff30a275ede36e5e2d893c21ad1ad599fb7716078e806ed2632212 +size 1707392288 diff --git a/Distilled-Qwen-3B-Coder.Q3_K_M.gguf b/Distilled-Qwen-3B-Coder.Q3_K_M.gguf new file mode 100644 index 0000000..0f072f0 --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7231be85c05d2d1ffbe6622227f23e8a4ee964a1c44b62002cc350fee86ebb75 +size 1590476064 diff --git a/Distilled-Qwen-3B-Coder.Q3_K_S.gguf b/Distilled-Qwen-3B-Coder.Q3_K_S.gguf new file mode 100644 index 0000000..40cd97b --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41cadc29ca11b9fdf9f7f53a18c786400e6c2b54c5bb4386015598555c7a402 +size 1454357792 diff --git a/Distilled-Qwen-3B-Coder.Q4_K_M.gguf b/Distilled-Qwen-3B-Coder.Q4_K_M.gguf new file mode 100644 index 0000000..b193e4f --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a297705a2b3078454af5209280aefab4bfbd22f53c3af0c623c0d62c1a85c5 +size 1929903392 diff --git a/Distilled-Qwen-3B-Coder.Q4_K_S.gguf b/Distilled-Qwen-3B-Coder.Q4_K_S.gguf new file mode 100644 index 0000000..214d8c0 --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371a673f8e03cc459c00c17e8bc86f5424d2d717838c343618d93ccfd9bc1405 +size 1834384672 diff --git a/Distilled-Qwen-3B-Coder.Q5_K_M.gguf b/Distilled-Qwen-3B-Coder.Q5_K_M.gguf new file mode 100644 index 0000000..220968c --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc5302f9300aeab80c4406c60d622ebb5c7668d72739acb0531708ef1c8088b +size 2224815392 diff --git a/Distilled-Qwen-3B-Coder.Q5_K_S.gguf b/Distilled-Qwen-3B-Coder.Q5_K_S.gguf new file mode 100644 index 0000000..34de9ef --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4466c73aedab6faa02a44fffe7bb583dc4df7fef08d1a0886ede0de1a4c437 +size 2169666848 diff --git a/Distilled-Qwen-3B-Coder.Q6_K.gguf b/Distilled-Qwen-3B-Coder.Q6_K.gguf new file mode 100644 index 0000000..1038c8c --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d0e675d88d5733826e6619bf25acc890ded859135a17f9f75ced516f82d4d8 +size 2538159392 diff --git a/Distilled-Qwen-3B-Coder.Q8_0.gguf b/Distilled-Qwen-3B-Coder.Q8_0.gguf new file mode 100644 index 0000000..669d733 --- /dev/null +++ b/Distilled-Qwen-3B-Coder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10c7a56734077551937006c89e3261c3a2aa533baeafc499740e6608221a8bd +size 3285476640 diff --git a/Distilled-Qwen-3B-Coder.f16.gguf b/Distilled-Qwen-3B-Coder.f16.gguf new file mode 100644 index 0000000..10d2612 --- /dev/null +++ b/Distilled-Qwen-3B-Coder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e958e21a9962b394bab94bc45461d4ccf5fa328a3d249faac51e2b4553056ce6 +size 6178317600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3f1139b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: hareeswar/Distilled-Qwen-3B-Coder +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hareeswar/Distilled-Qwen-3B-Coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Distilled-Qwen-3B-Coder-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-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/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Distilled-Qwen-3B-Coder-GGUF/resolve/main/Distilled-Qwen-3B-Coder.f16.gguf) | f16 | 6.3 | 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. + +