commit b1e9db1353d52043b576e18c48e30587be6fd5d9 Author: ModelHub XC Date: Sat May 9 08:55:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c9812e4 --- /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 +Qwen2.5-7B-DeepSeek-R1-1M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-DeepSeek-R1-1M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.IQ4_XS.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.IQ4_XS.gguf new file mode 100644 index 0000000..d901697 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d40c0dc37c487fb72e4ef9f1a9dfe33111d862ae29ba6963bf4010cec83e26 +size 4250299488 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q2_K.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q2_K.gguf new file mode 100644 index 0000000..7626ad8 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7dfe84f53e5687ce1a20cc09d39de53d2566cd080a57e0352034b678e98869 +size 3015941216 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_L.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_L.gguf new file mode 100644 index 0000000..33e4e9f --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f92df5329b067f3aee4ece7f9beeeb8a205018b9ae302690f3eb3b030c7427e +size 4088460384 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_M.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_M.gguf new file mode 100644 index 0000000..65eea09 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18a04b24620d792778e0ca9f913b9fa7dfc9c1ebe28b69c738b1320c0a0df1b7 +size 3808392288 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_S.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_S.gguf new file mode 100644 index 0000000..d24e67f --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc09c5bdbd08fba898e01817cd0f04f86d1b506024935a7082982af4a238266 +size 3492369504 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_M.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_M.gguf new file mode 100644 index 0000000..c970aa0 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30bec3263956a919b5fa7ff8aff4ff100b169878e0e5fc099596818f499d4fe0 +size 4683074656 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_S.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_S.gguf new file mode 100644 index 0000000..cc77692 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b1e10636c6126ae65cbbdb6a4bbed1e59bb9a657892de1789d492126c2134d +size 4457770080 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_M.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_M.gguf new file mode 100644 index 0000000..bbf81cd --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c5341ad248a45f9ab9f259c075e2d6ad7b7095a603aeceb1bcd2cd3a44bde7 +size 5444832352 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_S.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_S.gguf new file mode 100644 index 0000000..b35956e --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a291876a5f2998f5f36d4f241b9f58bc43c19bec99da701a4b2e3838841150f8 +size 5315177568 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q6_K.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q6_K.gguf new file mode 100644 index 0000000..624d138 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c11d8947d8598c2e441e7ac204de00400c07d044cee026943286cc477a90524 +size 6254199904 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.Q8_0.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.Q8_0.gguf new file mode 100644 index 0000000..0857620 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96eedf79f53ed9644cea941479d76efdd9ce4a83ef22e6caccf0821b0b75968c +size 8098526304 diff --git a/Qwen2.5-7B-DeepSeek-R1-1M.f16.gguf b/Qwen2.5-7B-DeepSeek-R1-1M.f16.gguf new file mode 100644 index 0000000..2f099f4 --- /dev/null +++ b/Qwen2.5-7B-DeepSeek-R1-1M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1383009161b7c3da11b68456134f4698a99dad0e5c6bfeb26d20ddd321839502 +size 15237854304 diff --git a/README.md b/README.md new file mode 100644 index 0000000..125437a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: prithivMLmods/Qwen2.5-7B-DeepSeek-R1-1M +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Qwen2.5-7B-DeepSeek-R1-1M + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-i1-GGUF +## 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/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-DeepSeek-R1-1M-GGUF/resolve/main/Qwen2.5-7B-DeepSeek-R1-1M.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +