commit 19f7a0173224524bd45caed9b72e0fcb6a82c1ee Author: ModelHub XC Date: Thu Jul 30 14:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RAG-R1-mq-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc0e953 --- /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 +RAG-R1-mq-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAG-R1-mq-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/RAG-R1-mq-7b.IQ4_XS.gguf b/RAG-R1-mq-7b.IQ4_XS.gguf new file mode 100644 index 0000000..bb41f80 --- /dev/null +++ b/RAG-R1-mq-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c6425db8470f3ca0113d1b05aa39c6912b63421ee86cb3e4f4f7cd028795a2 +size 4250297280 diff --git a/RAG-R1-mq-7b.Q2_K.gguf b/RAG-R1-mq-7b.Q2_K.gguf new file mode 100644 index 0000000..24f70e5 --- /dev/null +++ b/RAG-R1-mq-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96741361c54862f9611e3602b61a4a337fa45d9e2271a988df8314be637b1d30 +size 3015939008 diff --git a/RAG-R1-mq-7b.Q3_K_L.gguf b/RAG-R1-mq-7b.Q3_K_L.gguf new file mode 100644 index 0000000..8cc0fd8 --- /dev/null +++ b/RAG-R1-mq-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27bb45c33e2f48245afd6f06173eb2855d4f60ef7d42985bb36c556be6bbf1d +size 4088458176 diff --git a/RAG-R1-mq-7b.Q3_K_M.gguf b/RAG-R1-mq-7b.Q3_K_M.gguf new file mode 100644 index 0000000..8897e25 --- /dev/null +++ b/RAG-R1-mq-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811d39af7c10169460be7e5cec00d8065e6c3c2b2f466ac8cd620941b29b3689 +size 3808390080 diff --git a/RAG-R1-mq-7b.Q3_K_S.gguf b/RAG-R1-mq-7b.Q3_K_S.gguf new file mode 100644 index 0000000..a3506c9 --- /dev/null +++ b/RAG-R1-mq-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4669e7ad1ddc7ffe670bfd6cdc9c35a92ed0ee85c25232d81981c9f1884378b8 +size 3492367296 diff --git a/RAG-R1-mq-7b.Q4_K_M.gguf b/RAG-R1-mq-7b.Q4_K_M.gguf new file mode 100644 index 0000000..6651eaf --- /dev/null +++ b/RAG-R1-mq-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bdd145bc38a13c480d195706f25db2e15b5089708602dec9c28b99d545f7d64 +size 4683072448 diff --git a/RAG-R1-mq-7b.Q4_K_S.gguf b/RAG-R1-mq-7b.Q4_K_S.gguf new file mode 100644 index 0000000..3fd196e --- /dev/null +++ b/RAG-R1-mq-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd4f5b601ffc82a87347a48cbdec95c40ae733a1c71ff383cd6f874e882dd72 +size 4457767872 diff --git a/RAG-R1-mq-7b.Q5_K_M.gguf b/RAG-R1-mq-7b.Q5_K_M.gguf new file mode 100644 index 0000000..5af05ec --- /dev/null +++ b/RAG-R1-mq-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b907535e16886b6d28fc132609b703fef89cf0e2b6ab39a78ea1c3b08302a58 +size 5444830144 diff --git a/RAG-R1-mq-7b.Q5_K_S.gguf b/RAG-R1-mq-7b.Q5_K_S.gguf new file mode 100644 index 0000000..a83d24e --- /dev/null +++ b/RAG-R1-mq-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fa496aa0c1e9318d1aed50abe4964df0c9c89fc0a5cef6ed4ea6de944f1645 +size 5315175360 diff --git a/RAG-R1-mq-7b.Q6_K.gguf b/RAG-R1-mq-7b.Q6_K.gguf new file mode 100644 index 0000000..4c91919 --- /dev/null +++ b/RAG-R1-mq-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d22d9e017a1ab7600163d3b46acb2e16ffe61e548ab8a2b0e793bcd793399b +size 6254197696 diff --git a/RAG-R1-mq-7b.Q8_0.gguf b/RAG-R1-mq-7b.Q8_0.gguf new file mode 100644 index 0000000..ff3332f --- /dev/null +++ b/RAG-R1-mq-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db575fe43a2fe84857fb1782930f24394fe63aa511e0d08f55a429e6cb5b5a5b +size 8098524096 diff --git a/RAG-R1-mq-7b.f16.gguf b/RAG-R1-mq-7b.f16.gguf new file mode 100644 index 0000000..6263ef1 --- /dev/null +++ b/RAG-R1-mq-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f838f5289721845f797afd2522eb9249c7c7cd10e43ca90495d96381d57c594 +size 15237852096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..89ef835 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: yaoyueduzhen/RAG-R1-mq-7b +datasets: +- hotpotqa/hotpot_qa +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yaoyueduzhen/RAG-R1-mq-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RAG-R1-mq-7b-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/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RAG-R1-mq-7b-GGUF/resolve/main/RAG-R1-mq-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. + +