commit 96996ae3042daf7f0db670fa3d9c9a365a88a765 Author: ModelHub XC Date: Tue Apr 21 21:00:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7c664b --- /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-R1-Distill-Qwen-1.5B-S.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-S.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.IQ4_XS.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.IQ4_XS.gguf new file mode 100644 index 0000000..fb70c99 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc65c9a6b3fbb09019a39ec9c28cff4b1ea1e2f41be6b82b6d8cd437c2fa620d +size 1026162528 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q2_K.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q2_K.gguf new file mode 100644 index 0000000..ba8f8e9 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b4b3f80b3be793c3bb30290d50193d77bbc2e96ff008adc0516e055aaf276c +size 752880480 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_L.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_L.gguf new file mode 100644 index 0000000..ce42157 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b61f2a2416b6b472963de7dd103a53ccdaad298082ff20e38de3df6c4c87e24 +size 980440416 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_M.gguf new file mode 100644 index 0000000..2933972 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975f7996f52a214d984abda36201c8ac9410b4064679a415b0f80d784b36c8de +size 924456288 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_S.gguf new file mode 100644 index 0000000..7c6482c --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064a7c787c95ebb3dc247597bda82518d7a5a5e50959d0c9bdb011206e616ae8 +size 861222240 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_M.gguf new file mode 100644 index 0000000..5f17ec0 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80ad91805e02f4c30f1b0bec2e086b9f7ea218c41501d72e92cc40aa027aebc +size 1117321056 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_S.gguf new file mode 100644 index 0000000..0851f44 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e797b227205e9145b2f03a7313f276d8f736b6e3d6846da20546d23e53a40b +size 1071585120 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_M.gguf new file mode 100644 index 0000000..bc23424 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b9feb3357dc49e8ee53056e2aba576bd198b9ec0185809f210d4bdf302f284b +size 1285494624 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_S.gguf new file mode 100644 index 0000000..be99ffa --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6adb4554dda99f8ff0c5e19d213f92bd479d82dc0ed1e557653fa159b20859ba +size 1259173728 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q6_K.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q6_K.gguf new file mode 100644 index 0000000..1799b41 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f054e81d71743c7f147be79906820992d5f6f1a92b357bfe34ef82a906aaa1 +size 1464179040 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.Q8_0.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q8_0.gguf new file mode 100644 index 0000000..6008371 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b20ffb54fcf08691b0b6670d6280806a908912b4f782195f5412fb94335079b +size 1894532448 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-S.f16.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-S.f16.gguf new file mode 100644 index 0000000..1ecd305 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-S.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1496ad1fe9b1fc526ff06cce916169075e36f593b9fe38773571355d801df5b3 +size 3560416608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7c9268a --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: leonMW/DeepSeek-R1-Distill-Qwen-1.5B-S +datasets: AIML-TUDA/SLR-Bench +language: +- en +library_name: transformers +model_name: DeepSeek-R1-Distill-Qwen-1.5B-S +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/leonMW/DeepSeek-R1-Distill-Qwen-1.5B-S + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-Distill-Qwen-1.5B-S-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/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-S-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-S.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. + +