commit 28619ead4bf695add77ab9ae079862b4229bee81 Author: ModelHub XC Date: Mon Jul 6 11:20:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/prem-1B-grpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dedaafe --- /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 +prem-1B-grpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +prem-1B-grpo.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2d25a4 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ucalyptus/prem-1B-grpo +datasets: +- openai/gsm8k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- math +- reasoning +- grpo +- gsm8k +- reinforcement-learning +--- +## About + + + + + + +static quants of https://huggingface.co/ucalyptus/prem-1B-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/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/prem-1B-grpo-GGUF/resolve/main/prem-1B-grpo.f16.gguf) | f16 | 2.3 | 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. + + diff --git a/prem-1B-grpo.IQ4_XS.gguf b/prem-1B-grpo.IQ4_XS.gguf new file mode 100644 index 0000000..cb8cf3e --- /dev/null +++ b/prem-1B-grpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183a1b4d3d4d8fad1adfb9f2567e5ca75bcfbd62ce065fee8c0022882aae2c75 +size 609820096 diff --git a/prem-1B-grpo.Q2_K.gguf b/prem-1B-grpo.Q2_K.gguf new file mode 100644 index 0000000..41348a7 --- /dev/null +++ b/prem-1B-grpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027c8df4a248b1e18666931bfbdb05f77e1e5b7ae921d768901066224541ed11 +size 432142144 diff --git a/prem-1B-grpo.Q3_K_L.gguf b/prem-1B-grpo.Q3_K_L.gguf new file mode 100644 index 0000000..28041f3 --- /dev/null +++ b/prem-1B-grpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3b96f25580c94caa9cab7b8be9093c7e0b7816c3458767dc5eb3678e1d0b1f +size 591538816 diff --git a/prem-1B-grpo.Q3_K_M.gguf b/prem-1B-grpo.Q3_K_M.gguf new file mode 100644 index 0000000..f245f18 --- /dev/null +++ b/prem-1B-grpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20066749c04e0dce47901e653a56ca6fa06f49b2bded51f33bbcb8f134f270d5 +size 548416128 diff --git a/prem-1B-grpo.Q3_K_S.gguf b/prem-1B-grpo.Q3_K_S.gguf new file mode 100644 index 0000000..59d2873 --- /dev/null +++ b/prem-1B-grpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21d4aec05fe996badef487137a8f04546d826c97d5b1720b546c8b14d8e60a9 +size 499354240 diff --git a/prem-1B-grpo.Q4_K_M.gguf b/prem-1B-grpo.Q4_K_M.gguf new file mode 100644 index 0000000..803f448 --- /dev/null +++ b/prem-1B-grpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ba55323ed8f0b5a5d105a380926cbbdf9776523703ee312b569342ef9d3249 +size 667827904 diff --git a/prem-1B-grpo.Q4_K_S.gguf b/prem-1B-grpo.Q4_K_S.gguf new file mode 100644 index 0000000..13bda4f --- /dev/null +++ b/prem-1B-grpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00a091c32b98ee7c6d9f942fc0d705ea89e4c53ceba2401d3f90069765ef226 +size 639884992 diff --git a/prem-1B-grpo.Q5_K_M.gguf b/prem-1B-grpo.Q5_K_M.gguf new file mode 100644 index 0000000..803b9a9 --- /dev/null +++ b/prem-1B-grpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:920b55b0d97455654c58f5d7eeefede18264b95279238b43658dddc8f2b4447e +size 782058176 diff --git a/prem-1B-grpo.Q5_K_S.gguf b/prem-1B-grpo.Q5_K_S.gguf new file mode 100644 index 0000000..b8ca549 --- /dev/null +++ b/prem-1B-grpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc44e0c28283d04ec63a6c38053e9a57756f34542670c38038b5c40c9e311f3 +size 766042816 diff --git a/prem-1B-grpo.Q6_K.gguf b/prem-1B-grpo.Q6_K.gguf new file mode 100644 index 0000000..38b5f42 --- /dev/null +++ b/prem-1B-grpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4528111c766f0cea2b8c19c940a65bb9af4f947c50be0f893c670c6fc771322 +size 903427840 diff --git a/prem-1B-grpo.Q8_0.gguf b/prem-1B-grpo.Q8_0.gguf new file mode 100644 index 0000000..b234e7f --- /dev/null +++ b/prem-1B-grpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eef01146fc6c9294ccdb218c4a5fd89b2b9e7e9a5c1dad189aa99d17ec072ab +size 1169827456 diff --git a/prem-1B-grpo.f16.gguf b/prem-1B-grpo.f16.gguf new file mode 100644 index 0000000..3c65dff --- /dev/null +++ b/prem-1B-grpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512f33ccc893310528eb824bc68be8eb202be5d6283bf9a4f3ddf9ec9bffda0f +size 2201051776