commit 1c4ca811384409251296858c065567b7688f4dba Author: ModelHub XC Date: Thu Jul 30 03:57:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R1-Qwen2.5-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f393be7 --- /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 +R1-Qwen2.5-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R1-Qwen2.5-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R1-Qwen2.5-7B-Instruct.IQ4_XS.gguf b/R1-Qwen2.5-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..8fc7eb8 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cd67a04323ab8c0cac04c61ad1c296a877d89da36e2fc05abee9c573fb86a9 +size 4250299168 diff --git a/R1-Qwen2.5-7B-Instruct.Q2_K.gguf b/R1-Qwen2.5-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..bbc24b5 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820ad2e35e30b1bcf99b7001d40c3e73135ce561c850556f9ac0b813d5f6bc4a +size 3015940896 diff --git a/R1-Qwen2.5-7B-Instruct.Q3_K_L.gguf b/R1-Qwen2.5-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..713626e --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bc0b48e3f913c4bb6fb05f27284fdd95c5c5eaff8915dd556c0daa3c83d8f8 +size 4088460064 diff --git a/R1-Qwen2.5-7B-Instruct.Q3_K_M.gguf b/R1-Qwen2.5-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0032e51 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf83c878f285dee28f8fd756e0657eecce79990eda03d39a2e8605d0e3b2aa00 +size 3808391968 diff --git a/R1-Qwen2.5-7B-Instruct.Q3_K_S.gguf b/R1-Qwen2.5-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..78a89d2 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2873d1e5b12e527e08f1e5442998ff79e2aeea5d97af8f99dcd15b63dd9073 +size 3492369184 diff --git a/R1-Qwen2.5-7B-Instruct.Q4_K_M.gguf b/R1-Qwen2.5-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..d9dbda5 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f1577a2fa6663d1ee83e6499d08454ed382ddc2cc0ee2582932baf5db5f3afb +size 4683074336 diff --git a/R1-Qwen2.5-7B-Instruct.Q4_K_S.gguf b/R1-Qwen2.5-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..456b0b4 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb69d6667921a12caa671b3cd103e9dcf260a5250d70c4318bd19e37ca03bf02 +size 4457769760 diff --git a/R1-Qwen2.5-7B-Instruct.Q5_K_M.gguf b/R1-Qwen2.5-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..29e7468 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d0b6c70c80357555901101bbcd177d4269bc4c92ed9b8af96450092b910096d +size 5444832032 diff --git a/R1-Qwen2.5-7B-Instruct.Q5_K_S.gguf b/R1-Qwen2.5-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..5fcb51e --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e14842fea7687ff3667df46439315590bee329111705d7064c053970481d366 +size 5315177248 diff --git a/R1-Qwen2.5-7B-Instruct.Q6_K.gguf b/R1-Qwen2.5-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..ed5c32a --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76768ede2e5962a449fc56fadc589bd224dedf0370f051de78211819397b273 +size 6254199584 diff --git a/R1-Qwen2.5-7B-Instruct.Q8_0.gguf b/R1-Qwen2.5-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ebc10d8 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93159c7ecf239054ade11587f82f64cceab34aebc0ea7c67ec90dea4a1267150 +size 8098525984 diff --git a/R1-Qwen2.5-7B-Instruct.f16.gguf b/R1-Qwen2.5-7B-Instruct.f16.gguf new file mode 100644 index 0000000..0aa7843 --- /dev/null +++ b/R1-Qwen2.5-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:febcdaddb7b870ce959091f7ddfb934a6a8f93a40dfecd19fe2dc856e6c89fe2 +size 15237853984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc277f7 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: pe-nlp/R1-Qwen2.5-7B-Instruct +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/pe-nlp/R1-Qwen2.5-7B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-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/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/R1-Qwen2.5-7B-Instruct-GGUF/resolve/main/R1-Qwen2.5-7B-Instruct.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. + +