commit e0b1a1aa5a9d626d778acd2dd6c376a61b270ea7 Author: ModelHub XC Date: Sat Jul 18 20:17:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d40df35 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Coder-1.5B-Merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-1.5B-Merged.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-1.5B-Merged.IQ4_XS.gguf b/Qwen2.5-Coder-1.5B-Merged.IQ4_XS.gguf new file mode 100644 index 0000000..0aa16d4 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f09cde578b51183ef3d0e10292125b6b3b9653a7542fce7ae2f3e53d8db858 +size 1026163264 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q2_K.gguf b/Qwen2.5-Coder-1.5B-Merged.Q2_K.gguf new file mode 100644 index 0000000..758b9ef --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff300da45c69ecf9d2a3292ca732bface17b740fce36795d25e7b63a7874c78 +size 752881216 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q3_K_L.gguf b/Qwen2.5-Coder-1.5B-Merged.Q3_K_L.gguf new file mode 100644 index 0000000..6146ac4 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ccd6b1dd113079845f35dad463a9f933ac10acabb9023c0df63e3facecd33b +size 980441152 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q3_K_M.gguf b/Qwen2.5-Coder-1.5B-Merged.Q3_K_M.gguf new file mode 100644 index 0000000..3ef0a30 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4bbbc55091fdfde297c0c5104ff0943822aa0d6fee1349d8ee96b45962d0fc +size 924457024 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q3_K_S.gguf b/Qwen2.5-Coder-1.5B-Merged.Q3_K_S.gguf new file mode 100644 index 0000000..5fe5a82 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782a3b1057d3254abdcd35ee95521314e0708a59daf51f129de1b38a09f59cbc +size 861222976 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q4_0_4_4.gguf b/Qwen2.5-Coder-1.5B-Merged.Q4_0_4_4.gguf new file mode 100644 index 0000000..f3c58fe --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b420e9d1730d4cb0545b71e9972142b1e4b34240db53631eb4b7f37ef4e64ac2 +size 1066228288 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q4_K_M.gguf b/Qwen2.5-Coder-1.5B-Merged.Q4_K_M.gguf new file mode 100644 index 0000000..1be8dd3 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedbec5a4995bf4132c81a15cdf294ee46ef7158d7a093f318921927730c93d2 +size 1117321792 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q4_K_S.gguf b/Qwen2.5-Coder-1.5B-Merged.Q4_K_S.gguf new file mode 100644 index 0000000..9e38d9f --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3606287d3233d472de4ec8485c8a5b6fd7f446c1f2ec4ff516214a12b7dccd +size 1071585856 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q5_K_M.gguf b/Qwen2.5-Coder-1.5B-Merged.Q5_K_M.gguf new file mode 100644 index 0000000..9c02ffa --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5653de1555b66b4dc912f5d5b336b0dadfb9948973907214326ca20c75506197 +size 1285495360 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q5_K_S.gguf b/Qwen2.5-Coder-1.5B-Merged.Q5_K_S.gguf new file mode 100644 index 0000000..9434b41 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09900023ce3534ac8b17b3854095f45d36def8e68dbf7aa1447b36a95feeaaee +size 1259174464 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q6_K.gguf b/Qwen2.5-Coder-1.5B-Merged.Q6_K.gguf new file mode 100644 index 0000000..5a3158b --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d46b712f12e0eea3ba081a341e96f2e9180218504e4c88dd6918f265790efd67 +size 1464179776 diff --git a/Qwen2.5-Coder-1.5B-Merged.Q8_0.gguf b/Qwen2.5-Coder-1.5B-Merged.Q8_0.gguf new file mode 100644 index 0000000..03a69c5 --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ae09c9ae32e3b3e8d3edb338fc73bca99cf0e469f268b9c57fe763f7769110 +size 1894533184 diff --git a/Qwen2.5-Coder-1.5B-Merged.f16.gguf b/Qwen2.5-Coder-1.5B-Merged.f16.gguf new file mode 100644 index 0000000..d3b6e1a --- /dev/null +++ b/Qwen2.5-Coder-1.5B-Merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef70149ab04a832aa4ad79504f014faaae7cf1eb9be860472466b52c58b12e3 +size 3560417344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..27056a5 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: vonjack/Qwen2.5-Coder-1.5B-Merged +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/vonjack/Qwen2.5-Coder-1.5B-Merged + + +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-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Merged-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Merged.f16.gguf) | f16 | 3.7 | 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. + +