commit 352145d80c9419454d9fbe2a83398ff29a822b5a Author: ModelHub XC Date: Mon Jun 15 23:40:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b2c085 --- /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 +BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BoT-DeepSeek-R1-Distill-Qwen-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.IQ4_XS.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.IQ4_XS.gguf new file mode 100644 index 0000000..d418e3a --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03b9e497dcf7ff2277eeaca9df5e10c747a4f338160261aa1bacda742e6a1a6 +size 4250298528 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q2_K.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q2_K.gguf new file mode 100644 index 0000000..f947979 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd76d30779e84e5203716ee3b35841ed065f1d21beb3a236ebac1bc20d024e3 +size 3015940256 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_L.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_L.gguf new file mode 100644 index 0000000..fc0083f --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a326a99a0236435fd602d4f4d8f60c8e100c074e845bbb73cfd129eeaff9fef +size 4088459424 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_M.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_M.gguf new file mode 100644 index 0000000..ffbe244 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3878d068880f61c929bcd1a61fdb06318f416277afd530c27c94c14b0e854ca +size 3808391328 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_S.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_S.gguf new file mode 100644 index 0000000..cef4250 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c891bb28bf088ba5aa433e62854b7b57f5aef3e51e01128980bd4e0b73255f7e +size 3492368544 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf new file mode 100644 index 0000000..c033b34 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345abd7e430c539e5f9fedc0bc51e09f1174bcf9503edd2daa2f278a3493243b +size 4683073696 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_S.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_S.gguf new file mode 100644 index 0000000..f52828d --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968bc7507bb47a628b9b9da93d038f86710f9326fc90b948f0fa422974b5187a +size 4457769120 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_M.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_M.gguf new file mode 100644 index 0000000..5b945c7 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fcf015dc5efe9c6e99501cce874552bb6e1a6a5319fba7e47fe2a6d7c90960a +size 5444831392 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_S.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_S.gguf new file mode 100644 index 0000000..48aef55 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca45f8910c2df9190d4759302e46604168e5506ebf2f08a7aa13b5236a88b9b7 +size 5315176608 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q6_K.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q6_K.gguf new file mode 100644 index 0000000..d0409d0 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85cd74f079fd9e5fe85457f790f5e8e874f1a386ce3fbff12dc4733d31ce4521 +size 6254198944 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf new file mode 100644 index 0000000..79e9898 --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6453baec00ce8e30f7bb86de1cc0ace297e18250cccc61d51a1dfdba0cc62b +size 8098525344 diff --git a/BoT-DeepSeek-R1-Distill-Qwen-7B.f16.gguf b/BoT-DeepSeek-R1-Distill-Qwen-7B.f16.gguf new file mode 100644 index 0000000..a2b5c1b --- /dev/null +++ b/BoT-DeepSeek-R1-Distill-Qwen-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4f9c17a140d93a89b70b0b5a79cc4e4d43d5f061094d2c25086db01d713385 +size 15237853344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d4e56ee --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-7B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-7B + + +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/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BoT-DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/BoT-DeepSeek-R1-Distill-Qwen-7B.f16.gguf) | f16 | 15.3 | 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. + +