commit 43627783675f06310185e08280239524a1deeede Author: ModelHub XC Date: Wed Jul 1 22:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..28d1ac9 --- /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 +AlphaMaze-v0.1-1.5B-GRPO-cp-600.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMaze-v0.1-1.5B-GRPO-cp-600.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.IQ4_XS.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.IQ4_XS.gguf new file mode 100644 index 0000000..774ecb8 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c018a4fb4c9d8fd8a55d5d9ac415396ed0f5f9e9ba48815e480736e64eb90c +size 1026163072 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q2_K.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q2_K.gguf new file mode 100644 index 0000000..3c4e757 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1594e06a80d75e9ba69cf218b51189372c17e3c43e75519e94395cbd706484c8 +size 752881024 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_L.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_L.gguf new file mode 100644 index 0000000..c13b3c4 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce012367811d7926f79d091630d69de18199e65805cdf0f369fe90f033e5be9 +size 980440960 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_M.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_M.gguf new file mode 100644 index 0000000..3a7ab2f --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58eb020fbd8080dd3700bddcd92bcd716dbd441143fd54800d71a85ff038891c +size 924456832 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_S.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_S.gguf new file mode 100644 index 0000000..6897b38 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838a63646e2f8dc459409985d917c3e5447664f42a05def365291969c4ca32fe +size 861222784 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_M.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_M.gguf new file mode 100644 index 0000000..fe0dd30 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b7e902f9530a4dc23508bf93f7bceb0746e33a40e4acd2c3fee01748b95f73 +size 1117321600 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_S.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_S.gguf new file mode 100644 index 0000000..6271a9b --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc1659ab100b2653da02c77b32c0a3e2e45738d0a6dee2fcae0f8372c3361dc +size 1071585664 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_M.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_M.gguf new file mode 100644 index 0000000..812223b --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb471eb3aed198596dd00ff4406d331c5ad1119e40be2ca7425e98cd809f42a +size 1285495168 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_S.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_S.gguf new file mode 100644 index 0000000..6922af8 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3593e2557b2784c95e9bdd11db6b621d55d3033ebbbd6160128b1a94ae571f +size 1259174272 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q6_K.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q6_K.gguf new file mode 100644 index 0000000..6adb5c9 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61366b29aff2b9bb6b273d6adfe74441df6fd0166781d3ee12e808c55f342efe +size 1464179584 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q8_0.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q8_0.gguf new file mode 100644 index 0000000..292426d --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260a80e2864a633939d632b87c6f90458a10172ad6e359e8c4f06e6fb0308369 +size 1894532992 diff --git a/AlphaMaze-v0.1-1.5B-GRPO-cp-600.f16.gguf b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.f16.gguf new file mode 100644 index 0000000..2121cb9 --- /dev/null +++ b/AlphaMaze-v0.1-1.5B-GRPO-cp-600.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34c99aaae8ec07fb7c88e359067bd2a15585003dd2ed88a8df6690623e47e08 +size 3560417152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0291e1 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: jan-hq/AlphaMaze-v0.1-1.5B-GRPO-cp-600 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/jan-hq/AlphaMaze-v0.1-1.5B-GRPO-cp-600 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AlphaMaze-v0.1-1.5B-GRPO-cp-600-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/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMaze-v0.1-1.5B-GRPO-cp-600-GGUF/resolve/main/AlphaMaze-v0.1-1.5B-GRPO-cp-600.f16.gguf) | f16 | 3.7 | 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. + +