commit aa30c2ef6e6f94c1c1543c2f7ed554ba3250a1ec Author: ModelHub XC Date: Thu Jul 23 04:18:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-2.5-7B-Simple-RL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7769705 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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 +Qwen-2.5-7B-Simple-RL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-Simple-RL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-2.5-7B-Simple-RL.IQ4_XS.gguf b/Qwen-2.5-7B-Simple-RL.IQ4_XS.gguf new file mode 100644 index 0000000..93d8a2a --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292835cc1031298a6a65471e2978ba08e7793d6f1d112a09af21fcb87ec0860a +size 4250298816 diff --git a/Qwen-2.5-7B-Simple-RL.Q2_K.gguf b/Qwen-2.5-7B-Simple-RL.Q2_K.gguf new file mode 100644 index 0000000..eb060de --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:547fe933addc6a9e84954f8e5c78aacb4cfd3554c302624eb85bebff1dbda374 +size 3015940544 diff --git a/Qwen-2.5-7B-Simple-RL.Q3_K_L.gguf b/Qwen-2.5-7B-Simple-RL.Q3_K_L.gguf new file mode 100644 index 0000000..40fe184 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ccc48c7963a843b214746400df794aabba85b27625204819b1f8e9a34c5a674 +size 4088459712 diff --git a/Qwen-2.5-7B-Simple-RL.Q3_K_M.gguf b/Qwen-2.5-7B-Simple-RL.Q3_K_M.gguf new file mode 100644 index 0000000..f38d07c --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12dd440defdcc32dd56dac328a6f2bad6d6d5ac9b0b804014fc34bb0a494b91 +size 3808391616 diff --git a/Qwen-2.5-7B-Simple-RL.Q3_K_S.gguf b/Qwen-2.5-7B-Simple-RL.Q3_K_S.gguf new file mode 100644 index 0000000..445e6a2 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9803eec841febea7a27b3ea00f41cbecbf3886170dd062215f4046e4ad0860 +size 3492368832 diff --git a/Qwen-2.5-7B-Simple-RL.Q4_K_M.gguf b/Qwen-2.5-7B-Simple-RL.Q4_K_M.gguf new file mode 100644 index 0000000..680d9b6 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10236c56f7d3c27d34c34badc30bcbc2ca5c69ef241508e93169edeed75ab86d +size 4683073984 diff --git a/Qwen-2.5-7B-Simple-RL.Q4_K_S.gguf b/Qwen-2.5-7B-Simple-RL.Q4_K_S.gguf new file mode 100644 index 0000000..a1a7e4e --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d2b28fde05f9adc63361a4576285f0ddd9876f506e40db0dbb1e41c16b8ed4 +size 4457769408 diff --git a/Qwen-2.5-7B-Simple-RL.Q5_K_M.gguf b/Qwen-2.5-7B-Simple-RL.Q5_K_M.gguf new file mode 100644 index 0000000..a97eddd --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2fec32b6c4a1c2672ca6a20ecd6d0c221e461792f5de7a12a7de01cb86945e +size 5444831680 diff --git a/Qwen-2.5-7B-Simple-RL.Q5_K_S.gguf b/Qwen-2.5-7B-Simple-RL.Q5_K_S.gguf new file mode 100644 index 0000000..fe56de7 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ea740fabae7d9d557220a6b60435643a50db75cffe6b93ca51f2fc0da8720e +size 5315176896 diff --git a/Qwen-2.5-7B-Simple-RL.Q6_K.gguf b/Qwen-2.5-7B-Simple-RL.Q6_K.gguf new file mode 100644 index 0000000..db15775 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd40b2e14bd0ffa20493fe788e6c3a0e4a7ed9e95b700b11853547f12c5b3b2 +size 6254199232 diff --git a/Qwen-2.5-7B-Simple-RL.Q8_0.gguf b/Qwen-2.5-7B-Simple-RL.Q8_0.gguf new file mode 100644 index 0000000..dd24ba9 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4bfc9b209b4c44c2ff79dc52bdb149cd3b1c12c754062eef1d78b3ec580d0da +size 8098525632 diff --git a/Qwen-2.5-7B-Simple-RL.f16.gguf b/Qwen-2.5-7B-Simple-RL.f16.gguf new file mode 100644 index 0000000..0c2a659 --- /dev/null +++ b/Qwen-2.5-7B-Simple-RL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976c3b74176872c8969ec5a23a3497f4987c9091863bd2fe0e224fe202f72eac +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a5da02 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: tpoisonooo/Qwen-2.5-7B-Simple-RL +language: +- en +library_name: transformers +model_name: Qwen-2.5-7B-Simple-RL +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/tpoisonooo/Qwen-2.5-7B-Simple-RL + + +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/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-Simple-RL-GGUF/resolve/main/Qwen-2.5-7B-Simple-RL.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. + +