commit 4a7587a67d4e0a8b47bc985e29ab59b6c989d7f6 Author: ModelHub XC Date: Thu Jun 4 08:57:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..27f1e21 --- /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 +Llama-3.2-3B-Instruct-skyt1-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-skyt1-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..757bdfa --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae4cc02cebb23974229bc3563f34296e0726be1d0d8c7370fc1b6703497edd5 +size 2050221248 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q2_K.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q2_K.gguf new file mode 100644 index 0000000..d84703d --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27249526c259d2952311050455a90956fbfbd978defdf81a344650a9af53a1cc +size 1493218496 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..32f22e5 --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77579620b4aee121178fd82565e19a64ce81d12f191e69e4786404792cfc2c93 +size 1984646336 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..694f60b --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0bfc124c86bf08389e66f2b2f1b4be942541f2c2556ad88f5fe54646e9bdb7 +size 1856457920 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..a0280da --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36abc145c5a2485485df0e8786175a60bce95472574fcdb3b3c43e0990ebe17b +size 1712147648 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..a5ffe4e --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:736a64d47ed57c0f3e63bfa3eb501b206d940cf09b4988aca0637575af1949fc +size 2241004736 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..414f74b --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6ea661f7ec161af721a42637d2971a54c2cefe1a363e22d318e5d88505995d +size 2149827776 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..007836f --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f66d7824333fc8a464819d5b68d808a7de4a1e3a97c3d9fd28c35caa8e7fdb5 +size 2593031360 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..8b6948e --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614931260fbcf890c9c83d2552e589ae9bbe670fe8e7584bcba765c94a76d6ba +size 2540389568 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q6_K.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q6_K.gguf new file mode 100644 index 0000000..0e4078d --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe73cb2518961323be8ae0b7b5f1bccafc259f5485fe1f8f47347b399c58f995 +size 2967059648 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.Q8_0.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q8_0.gguf new file mode 100644 index 0000000..62af022 --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6043831e6b32fb4cd35846e678f788bbce9589fc7a5546dbca6c1a6d952cf43d +size 3840527552 diff --git a/Llama-3.2-3B-Instruct-skyt1-GRPO.f16.gguf b/Llama-3.2-3B-Instruct-skyt1-GRPO.f16.gguf new file mode 100644 index 0000000..30c645a --- /dev/null +++ b/Llama-3.2-3B-Instruct-skyt1-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d9e9e8248bef557f7cc6f49b2de7066b2ecfb7a6f252dd5e5b32e52313dfd0 +size 7221693632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a752323 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: zztheaven/Llama-3.2-3B-Instruct-skyt1-GRPO +datasets: NovaSky-AI/Sky-T1_data_17k +language: +- en +library_name: transformers +model_name: Llama-3.2-3B-Instruct-skyt1-GRPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/zztheaven/Llama-3.2-3B-Instruct-skyt1-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-skyt1-GRPO-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/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-skyt1-GRPO-GGUF/resolve/main/Llama-3.2-3B-Instruct-skyt1-GRPO.f16.gguf) | f16 | 7.3 | 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. + +