commit 429162e70651e57fc446d7c63107c2778dd00048 Author: ModelHub XC Date: Thu May 7 16:03:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d486e68 --- /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 +RAIF-DeepSeek-Qwen-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RAIF-DeepSeek-Qwen-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/RAIF-DeepSeek-Qwen-1.5B.IQ4_XS.gguf b/RAIF-DeepSeek-Qwen-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..6b58025 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf67fa41bfe3c5867cd5545fa0073e6d36ef1ee8283d5af4b7f31c85890ce64 +size 1026162464 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q2_K.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q2_K.gguf new file mode 100644 index 0000000..681399f --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb03820bb8e8b5679e0d20a026bc4198b4bf113abdecbe8fe135a156b7d5d08 +size 752880416 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q3_K_L.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..b37ef5b --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e52e248cf762e7b0d05f2fe59a1c9d1395107b881e2e3216fb627ba5a1578a +size 980440352 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q3_K_M.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..c73c588 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b958909a05a96df6f970a4bfdfbd3eb9bdf86cd127559d150029b35a8c914b8c +size 924456224 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q3_K_S.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..78a961e --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f948b9b15ed316dcaddfcd16a8671f188c6d2f020110e62a025c15f93d603fe +size 861222176 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q4_K_M.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..aff7554 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d3ede601b6bccb6a70c194229158f15318e6bc5482cbbc5ef2c97f2c7c593c +size 1117320992 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q4_K_S.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..6016da6 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0639afb37645491ace6dc4f4d83ecb540e745db851a256e55e9b857b787d42aa +size 1071585056 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q5_K_M.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..1d5c569 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072166d1ff3daedd0d509101c0e596b4dff908ad3d257eab6622e6e176dff151 +size 1285494560 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q5_K_S.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..cbbb40c --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7e3c6ceeb2fed74e66a6e104a6d660300fec955174803fac66b20904034228 +size 1259173664 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q6_K.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q6_K.gguf new file mode 100644 index 0000000..1700bd3 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb39c9b7e1e2045f3608648f4cc22daadc421039375c2c80b6fb8933ba599b0 +size 1464178976 diff --git a/RAIF-DeepSeek-Qwen-1.5B.Q8_0.gguf b/RAIF-DeepSeek-Qwen-1.5B.Q8_0.gguf new file mode 100644 index 0000000..0635f47 --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587ecb08088b4a650ea1e80b8137f13edd843676acab9c4d1fb6154725ed0010 +size 1894532384 diff --git a/RAIF-DeepSeek-Qwen-1.5B.f16.gguf b/RAIF-DeepSeek-Qwen-1.5B.f16.gguf new file mode 100644 index 0000000..88559af --- /dev/null +++ b/RAIF-DeepSeek-Qwen-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3499941bea5a46542227fd7b60c86dc6c0ee2652aa45d20a3e96c4b76c455f75 +size 3560416544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..752f846 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: yolay/RAIF-DeepSeek-Qwen-1.5B +datasets: +- yolay/RAIF-ComplexInstruction-DeepSeek +language: en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yolay/RAIF-DeepSeek-Qwen-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RAIF-DeepSeek-Qwen-1.5B-GGUF).*** + +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/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RAIF-DeepSeek-Qwen-1.5B-GGUF/resolve/main/RAIF-DeepSeek-Qwen-1.5B.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. + +