commit 1328b4941bf421f92dc16cb8d66c67666f3d18c1 Author: ModelHub XC Date: Sat Jul 18 06:55:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88f4936 --- /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 +Qwen2.5.1-Coder-1.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5.1-Coder-1.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.IQ4_XS.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..8fec42e --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6ea5e68bf6559b4edc8b26f58265490a0a4071f8b1a7aa0f7791a689d18c31 +size 902183456 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q2_K.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..dbf2fcf --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a80603089b703132e5952fb1346bfaef995d826c53c384607d96d0ed129fcb +size 676305440 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_L.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6504988 --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4594ea71f60ada331b4020292c47c7bc4db4bba2eed977efae55f22acf5dad +size 880163360 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_M.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..5acb30c --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccdf468c40d1ff040f066b4c46654a5e8f5115cbf8d21a2db3aad1e46787b1db +size 824179232 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_S.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..5f3def2 --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10de5294516291d5af1bb9370ee77d3a6c20102386d539d8f54e18d2dd6799a8 +size 760945184 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_M.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..9db2bb1 --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c543ad7abf84f9f7914661a8722ac3c6c4bf5448465499cb77f63f77cab9cc8 +size 986049056 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_S.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..709c552 --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2320b2d89af8a940e777a47e9439b521a2a9c8726f1fba1822039a644a61d043 +size 940313120 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_M.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..57d9646 --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d08573da75e7a5fbc5c8fff566c8206757267ea1448916fa7db3b832ee824c75 +size 1125050912 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_S.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..5f4668b --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0af9c1457d08e5ea76531fe28d600f341e57b8edf1b2c6b90bfdb9842cc585 +size 1098730016 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q6_K.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..530406a --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb4f2f498a97dc0bb9bbd429c0916325ab05c6242705575dbbfbd300e5f8db5 +size 1272740384 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.Q8_0.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..95e9db4 --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c82055527a91ff52a4e0627c0ab1267b4745c427b10226b5740816b34a931a +size 1646573600 diff --git a/Qwen2.5.1-Coder-1.5B-Instruct.f16.gguf b/Qwen2.5.1-Coder-1.5B-Instruct.f16.gguf new file mode 100644 index 0000000..6c8cdec --- /dev/null +++ b/Qwen2.5.1-Coder-1.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24545ce0c1213c5c0eb6466c5ee4b9ae1daaafc1cc3bd5ed63370475856f0fbe +size 3093669920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34b56cd --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: QuantPanda/Qwen2.5.1-Coder-1.5B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/main/LICENSE +quantized_by: mradermacher +tags: +- code +- codeqwen +- chat +- qwen +- qwen-coder +--- +## About + + + + + + +static quants of https://huggingface.co/QuantPanda/Qwen2.5.1-Coder-1.5B-Instruct + + +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/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5.1-Coder-1.5B-Instruct-GGUF/resolve/main/Qwen2.5.1-Coder-1.5B-Instruct.f16.gguf) | f16 | 3.2 | 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. + +