commit 9ea36e055c3cbf43dd26a9c3cd77b20a0a056439 Author: ModelHub XC Date: Thu Jun 11 07:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fd556f5 --- /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-ComputerScience-COT-Qwen-7B-FineTuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.IQ4_XS.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.IQ4_XS.gguf new file mode 100644 index 0000000..48bb616 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e41ac115ce452d4d2036ed5ea98e8d1261bedfc5f3baf50030afe118f1674f +size 4250299232 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q2_K.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q2_K.gguf new file mode 100644 index 0000000..9ca0a72 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d539eb5d85df60ea0fda590181371ad1223cf372c149a602a27be2cb69c61af +size 3015940960 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_L.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_L.gguf new file mode 100644 index 0000000..8235f84 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b777c1a1a987225fedb9bff38219edb012456ad59abd1a927e6a16c4ac63d448 +size 4088460128 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_M.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_M.gguf new file mode 100644 index 0000000..4e8ebdc --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcf69b5744a1d5503ff647517038e611e5a35124d82a3d05b967c55d83f3ff4 +size 3808392032 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_S.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_S.gguf new file mode 100644 index 0000000..642dbcf --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707db813dab33213455ad13c8efe09323ebf4546266efdf00c777b2dadda69b7 +size 3492369248 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_M.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_M.gguf new file mode 100644 index 0000000..c2013eb --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35cb11a3eec62d8600c44876eeb7338a10e197942d6b82f0ada592f6a8c76a68 +size 4683074400 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_S.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_S.gguf new file mode 100644 index 0000000..5dbee61 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd860eed27c43337155170671af5b29226f6d7d06ea2a09499f701a2304b85b +size 4457769824 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_M.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_M.gguf new file mode 100644 index 0000000..a91a05f --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a683a9071b70a50b4c2c075f9a9ac982f4419af38ab8b621722e562e38d757 +size 5444832096 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_S.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_S.gguf new file mode 100644 index 0000000..dc5b019 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92aa72b2385ca4b773127063ee5bcdfe4511111f82216d4a479b4098f3547f7f +size 5315177312 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q6_K.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q6_K.gguf new file mode 100644 index 0000000..d4d51b0 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad534404ed7dea23d32223e05100b87d24e0e1afe3fc3fa101da87d9b077b166 +size 6254199648 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q8_0.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q8_0.gguf new file mode 100644 index 0000000..794d373 --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5f270902f69302dc1fa477ae03be7e0f9b44138a7652f8ca92255495709165 +size 8098526048 diff --git a/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.f16.gguf b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.f16.gguf new file mode 100644 index 0000000..dc7a63c --- /dev/null +++ b/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba873b6aaab706bfb12ff94a4f00471d118e52c4951b5283a95a15c2e9c8860c +size 15237854048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3eb6c91 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: wochaori/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/wochaori/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-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-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned-GGUF/resolve/main/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned.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. + +