commit a5ecaa4fed41133ef1d87c23cb765009a019f7aa Author: ModelHub XC Date: Mon Jun 15 02:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f4b21a4 --- /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 +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.IQ4_XS.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.IQ4_XS.gguf new file mode 100644 index 0000000..ac3b0a9 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdad12eec616e266bb5e970c3fbb314e96b2da9867d1165d6323085f80d72bd8 +size 4250298816 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q2_K.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q2_K.gguf new file mode 100644 index 0000000..e2f286b --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5eb5ac3cd8da78c0c7496d05cae8ea5ed31bdaac654476b203fc97a1ad925c +size 3015940544 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_L.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_L.gguf new file mode 100644 index 0000000..fd176ac --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1580f0ca7883647d307c711af51e2404de4ec0f673fb2c107468e1806329d0 +size 4088459712 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_M.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_M.gguf new file mode 100644 index 0000000..8243382 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c71445049581509cd3e9b7f77ef1414f3f2debeacb325e0b37637fbfcb6e8a32 +size 3808391616 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_S.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_S.gguf new file mode 100644 index 0000000..ec5746d --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce3ac319a7621a7e69c82607fcce65c02a2149087e62f0acd268ccf5c7ffe1d +size 3492368832 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_M.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_M.gguf new file mode 100644 index 0000000..f5f824a --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9509a9121283bdff87f293bb7017e32c1a4e400628290c5e6ae9a926fe11d329 +size 4683073984 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_S.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_S.gguf new file mode 100644 index 0000000..aab63d1 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d62c3e82d48d07d1c8c33e4ce50b17b7d380ae3eec28737f8d0441bcb8db27 +size 4457769408 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_M.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_M.gguf new file mode 100644 index 0000000..94f2075 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a4753bbb667f120366468f34012d7bc6880529049e458fe78b1c6680ba33aa +size 5444831680 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_S.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_S.gguf new file mode 100644 index 0000000..b057add --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92468fe897a6f4ae5ef5580c94ae59659c4577ef1614951889df3c7f9c2c15c +size 5315176896 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q6_K.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q6_K.gguf new file mode 100644 index 0000000..2bdc984 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40c8c58dbd5e46fca29e14fd3a5d01450a5fb7c63e53785e2ca6bea77d04bc6 +size 6254199232 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q8_0.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q8_0.gguf new file mode 100644 index 0000000..848b451 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e12e314f08aae0122c44640a9f184968affdbee96b4bf1d7d87ccc373f1b23 +size 8098525632 diff --git a/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.f16.gguf b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.f16.gguf new file mode 100644 index 0000000..1b06018 --- /dev/null +++ b/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80e5bd0b0e3999ca1bb7fac2597a5745046421d9046b935661f497bb5d21c27 +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3e203e8 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Rano23/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Rano23/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-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/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k-GGUF/resolve/main/OpenR1-Qwen-7B-Instruct-SFT-lora-ctx16k.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. + +