commit 6dccb9fe55874ebb9a16f45a084be040a61a4e8d Author: ModelHub XC Date: Mon Aug 3 16:59:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3b-bs128-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e552ab7 --- /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 +Qwen3b-bs128-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3b-bs128-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3b-bs128-GRPO.IQ4_XS.gguf b/Qwen3b-bs128-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..fc4a52d --- /dev/null +++ b/Qwen3b-bs128-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6094a1733bb7e8f38b411c2540a1d683287375736900469df93ca84eb93d60f7 +size 1918491264 diff --git a/Qwen3b-bs128-GRPO.Q2_K.gguf b/Qwen3b-bs128-GRPO.Q2_K.gguf new file mode 100644 index 0000000..7310bab --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90fed205e19423c916b2fbdb97f071452873ae7c49e5e86471cbfa1a659c4d0d +size 1376856704 diff --git a/Qwen3b-bs128-GRPO.Q3_K_L.gguf b/Qwen3b-bs128-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..daabd6d --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ccd38724aae9c6c84af02b0e8f21484285e36de0c81cadb2409b8d01a9584b +size 1841095296 diff --git a/Qwen3b-bs128-GRPO.Q3_K_M.gguf b/Qwen3b-bs128-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..86ba9dd --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae994a236742ec4fc6d34743e714d030317f04a97ee1b4a9aa6ae2665cb52302 +size 1724179072 diff --git a/Qwen3b-bs128-GRPO.Q3_K_S.gguf b/Qwen3b-bs128-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..c7bec46 --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4058511fd19a84754767381df138192f4c708ce5c85d56e71ab69e9d698f89d8 +size 1588060800 diff --git a/Qwen3b-bs128-GRPO.Q4_K_M.gguf b/Qwen3b-bs128-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..6f80a0f --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bcbf034111073f2d805bf09fd7f4c42a7cf97c348d7cbecec981f665550a929 +size 2104932992 diff --git a/Qwen3b-bs128-GRPO.Q4_K_S.gguf b/Qwen3b-bs128-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..6b367d8 --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a56cf873f8a7266cc331151e58b07435b5418d109a154ee6b03db99b70fe9cda +size 2009414272 diff --git a/Qwen3b-bs128-GRPO.Q5_K_M.gguf b/Qwen3b-bs128-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..0093787 --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daff7f882a509157e43b0a1ac1a4d2642a6021c4bb7c2bdaa3ca947fc27327a6 +size 2438740608 diff --git a/Qwen3b-bs128-GRPO.Q5_K_S.gguf b/Qwen3b-bs128-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..3b087b8 --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0133fc258474d2e97d63c719c5fbf919ac3aeea12d76e3060eabc90711c74389 +size 2383592064 diff --git a/Qwen3b-bs128-GRPO.Q6_K.gguf b/Qwen3b-bs128-GRPO.Q6_K.gguf new file mode 100644 index 0000000..1d9c6dc --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ffb1bc16a7f55847b11ffe8c02ed0b518f2f8fc0d1a855b6a2610b9700447c +size 2793411200 diff --git a/Qwen3b-bs128-GRPO.Q8_0.gguf b/Qwen3b-bs128-GRPO.Q8_0.gguf new file mode 100644 index 0000000..d98a8c0 --- /dev/null +++ b/Qwen3b-bs128-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a182c635f342c7e0df57fa01875db7dd7fd74361cce9efd7b19c1f02c3dbfda2 +size 3616088704 diff --git a/Qwen3b-bs128-GRPO.f16.gguf b/Qwen3b-bs128-GRPO.f16.gguf new file mode 100644 index 0000000..a7aaa30 --- /dev/null +++ b/Qwen3b-bs128-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6143d842006e94f38caaaea30ac7577bf33b6c14ce0f77840abf82fd7032a32 +size 6800646784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..600a095 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: RLAIF/Qwen3b-bs128-GRPO +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/RLAIF/Qwen3b-bs128-GRPO + + +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/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3b-bs128-GRPO-GGUF/resolve/main/Qwen3b-bs128-GRPO.f16.gguf) | f16 | 6.9 | 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. + +