commit c43821bfbb2ccc09b8ef0814032f5377eed77c66 Author: ModelHub XC Date: Sun Jul 19 11:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a073db1 --- /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 +Deepseek-Qwen2.5-1.5B-Redistil.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Deepseek-Qwen2.5-1.5B-Redistil.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.IQ4_XS.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.IQ4_XS.gguf new file mode 100644 index 0000000..c7de1a9 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2195e30398f34c607141bf0437eb99bb1f96e7a2893667705934fef1f93c1116 +size 1026162432 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q2_K.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q2_K.gguf new file mode 100644 index 0000000..04fd030 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236d4537fd3c83fe9070dac4690436329ad901854995dcc6d6f00b5a6ffa8cd3 +size 752880384 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_L.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_L.gguf new file mode 100644 index 0000000..c555361 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9e9664591c4bb6f9c97b8c81ed02cfe3b636f69b5f5f276a2e9bb43c2a3a02 +size 980440320 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_M.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_M.gguf new file mode 100644 index 0000000..898f9f3 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26812eb9b7ea9c9e30bd681f169b1c8c8ea07f3b84e9acf550342a9ba50f1e9 +size 924456192 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_S.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_S.gguf new file mode 100644 index 0000000..7498a0e --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9105b2bce51cfccc7a276e6bb92fa24e87cacc880ccf1ab9842d0b3acb421afd +size 861222144 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_M.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_M.gguf new file mode 100644 index 0000000..5578229 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5f22ee278f0a86ed944cbecc850c04fa365700ba41ddad987e506e17e6ac79 +size 1117320960 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_S.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_S.gguf new file mode 100644 index 0000000..d18ca4a --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26148784c2bd0596c770c7e71fbce0efe1071e4a336a4352e41255d791049793 +size 1071585024 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_M.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_M.gguf new file mode 100644 index 0000000..7b919c8 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c40d6feb7356db4e83d1ffb777b2e10caa7aa1ee7b8f712afffb18e31ea781e +size 1285494528 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_S.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_S.gguf new file mode 100644 index 0000000..5a96663 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190c4bcf5f9a8c1a16d1196833e4bb9d244da12ee4ea080aa803da2ac47a432b +size 1259173632 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q6_K.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q6_K.gguf new file mode 100644 index 0000000..5165103 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022713669ae580df02bd863f0dd4d79c44e6cc7664389ba0c72d1328ec774bd9 +size 1464178944 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.Q8_0.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.Q8_0.gguf new file mode 100644 index 0000000..07a43e8 --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5adb77ef62d2f50bd938f1fcde48622357b7b287d03d61f15d1bed26c109fdf0 +size 1894532352 diff --git a/Deepseek-Qwen2.5-1.5B-Redistil.f16.gguf b/Deepseek-Qwen2.5-1.5B-Redistil.f16.gguf new file mode 100644 index 0000000..23de02b --- /dev/null +++ b/Deepseek-Qwen2.5-1.5B-Redistil.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34f996952531769fa32b416f85a48c68257a79a8c28c22646e44ed0fa43a303 +size 3560416512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..339c96f --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: jan-hq/Deepseek-Qwen2.5-1.5B-Redistil +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jan-hq/Deepseek-Qwen2.5-1.5B-Redistil + + +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/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Deepseek-Qwen2.5-1.5B-Redistil-GGUF/resolve/main/Deepseek-Qwen2.5-1.5B-Redistil.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. + +