commit 1cba224209b4bd9fb9e5100a2df4551c63f983a9 Author: ModelHub XC Date: Sun May 24 23:06:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1_3B_GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d203ed --- /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 +Llama3.1_3B_GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_3B_GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1_3B_GRPO.IQ4_XS.gguf b/Llama3.1_3B_GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..3a25da7 --- /dev/null +++ b/Llama3.1_3B_GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00283a0257ae55fd88ae29789623c3489df8cf13d806fe1d18dd9fa7f06c6d6b +size 1840906720 diff --git a/Llama3.1_3B_GRPO.Q2_K.gguf b/Llama3.1_3B_GRPO.Q2_K.gguf new file mode 100644 index 0000000..563dbcd --- /dev/null +++ b/Llama3.1_3B_GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4380c4f057b60466d2d9abef1f162d4b3c62de396dba0536e084bdf023f67e5 +size 1363935712 diff --git a/Llama3.1_3B_GRPO.Q3_K_L.gguf b/Llama3.1_3B_GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..9d3012a --- /dev/null +++ b/Llama3.1_3B_GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ecb7da409b92ed6f8836a98d34fde8ba203c6cf7afabbb80c3123ebfce0f671 +size 1815347680 diff --git a/Llama3.1_3B_GRPO.Q3_K_M.gguf b/Llama3.1_3B_GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..d35d34b --- /dev/null +++ b/Llama3.1_3B_GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31403f530764d20244dd89d042d51b8d8a7d29ffe48bd32338cf72fe8b76d76 +size 1687159264 diff --git a/Llama3.1_3B_GRPO.Q3_K_S.gguf b/Llama3.1_3B_GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..18e9ef3 --- /dev/null +++ b/Llama3.1_3B_GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b84c18415fb819ae93d769dba55c0455f20ddeba8c298e00d6e736e8127fc5 +size 1542848992 diff --git a/Llama3.1_3B_GRPO.Q4_K_M.gguf b/Llama3.1_3B_GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..6673e10 --- /dev/null +++ b/Llama3.1_3B_GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb274fb3972944e6756f937c449a1c7ab72c1f21941a7ba485650a2b2598b80 +size 2019377632 diff --git a/Llama3.1_3B_GRPO.Q4_K_S.gguf b/Llama3.1_3B_GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..8d3b5b2 --- /dev/null +++ b/Llama3.1_3B_GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5aa975bafc37a6dcb6f968cafb89413977b1b30cacbcf7a58b9ba8e6eca4df +size 1928200672 diff --git a/Llama3.1_3B_GRPO.Q5_K_M.gguf b/Llama3.1_3B_GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..b38e1c4 --- /dev/null +++ b/Llama3.1_3B_GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5413ea52a53ad6915ed59d99cda20325842118d60c355b80a356c7fcf15e88b +size 2322153952 diff --git a/Llama3.1_3B_GRPO.Q5_K_S.gguf b/Llama3.1_3B_GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..558de0e --- /dev/null +++ b/Llama3.1_3B_GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d20dd1cdee18674012ce39354b3ca777fc24d7b580642db5599abcfbb4e152 +size 2269512160 diff --git a/Llama3.1_3B_GRPO.Q6_K.gguf b/Llama3.1_3B_GRPO.Q6_K.gguf new file mode 100644 index 0000000..add210c --- /dev/null +++ b/Llama3.1_3B_GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d39c9cee689f613f1e86754de387e46443ce5fff952ab0277bd4a77c523cb81 +size 2643853792 diff --git a/Llama3.1_3B_GRPO.Q8_0.gguf b/Llama3.1_3B_GRPO.Q8_0.gguf new file mode 100644 index 0000000..10a0510 --- /dev/null +++ b/Llama3.1_3B_GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d70dd87371d4ea9703c19b171f851abed9828f6f78a657a23f745b4368dbf8e6 +size 3421899232 diff --git a/Llama3.1_3B_GRPO.f16.gguf b/Llama3.1_3B_GRPO.f16.gguf new file mode 100644 index 0000000..6bb4478 --- /dev/null +++ b/Llama3.1_3B_GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8a7a5c9b6d16d36ff9e8e345b6dfe62e90de2b77cd390fbd53c5ae06851a88 +size 6433688032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f261c4c --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: CALISTA-INDUSTRY/Llama3.1_3B_GRPO +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/CALISTA-INDUSTRY/Llama3.1_3B_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/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_3B_GRPO-GGUF/resolve/main/Llama3.1_3B_GRPO.f16.gguf) | f16 | 6.5 | 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. + +