commit dbec4f0a44d7d1a015d834eb25f4944cf4de488b Author: ModelHub XC Date: Tue May 26 04:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRLHF-2B-Pretrained-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9591e0d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +GRLHF-2B-Pretrained.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-2B-Pretrained.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRLHF-2B-Pretrained.IQ4_XS.gguf b/GRLHF-2B-Pretrained.IQ4_XS.gguf new file mode 100644 index 0000000..b70b139 --- /dev/null +++ b/GRLHF-2B-Pretrained.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d63460a565c935673cfd81698053ec61a73cb1416f97281fd02b97dc8428a663 +size 1026161216 diff --git a/GRLHF-2B-Pretrained.Q2_K.gguf b/GRLHF-2B-Pretrained.Q2_K.gguf new file mode 100644 index 0000000..5d77c9d --- /dev/null +++ b/GRLHF-2B-Pretrained.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529975a206aee87fa40c10075f588ab8f262c1801d4ede54599d4c0bf7a6a265 +size 752879168 diff --git a/GRLHF-2B-Pretrained.Q3_K_L.gguf b/GRLHF-2B-Pretrained.Q3_K_L.gguf new file mode 100644 index 0000000..9238d3e --- /dev/null +++ b/GRLHF-2B-Pretrained.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd26baa6a4e55487bdb970ec8b32e957c4a09c450a1f3545d4096d00ab6cc30 +size 980439104 diff --git a/GRLHF-2B-Pretrained.Q3_K_M.gguf b/GRLHF-2B-Pretrained.Q3_K_M.gguf new file mode 100644 index 0000000..9fc0aeb --- /dev/null +++ b/GRLHF-2B-Pretrained.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e2e16ae54605c87854f7d43cbfd807ad5d354b19937b90130e635474ad7c86 +size 924454976 diff --git a/GRLHF-2B-Pretrained.Q3_K_S.gguf b/GRLHF-2B-Pretrained.Q3_K_S.gguf new file mode 100644 index 0000000..256b72d --- /dev/null +++ b/GRLHF-2B-Pretrained.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df9673aaedd0db3acb4d5b4fe57837b6a35376ae53c3728da631028f36727dc +size 861220928 diff --git a/GRLHF-2B-Pretrained.Q4_K_M.gguf b/GRLHF-2B-Pretrained.Q4_K_M.gguf new file mode 100644 index 0000000..fa2c0c0 --- /dev/null +++ b/GRLHF-2B-Pretrained.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c40e6a2630f1f72e8f8f319cb8f03142ed1bdeca8aed8d476438d8501eae7512 +size 1117319744 diff --git a/GRLHF-2B-Pretrained.Q4_K_S.gguf b/GRLHF-2B-Pretrained.Q4_K_S.gguf new file mode 100644 index 0000000..950477c --- /dev/null +++ b/GRLHF-2B-Pretrained.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c983f482257a9f22df89974f7f4c4a759146275e91e4b3ab64cc98445b237ec +size 1071583808 diff --git a/GRLHF-2B-Pretrained.Q5_K_M.gguf b/GRLHF-2B-Pretrained.Q5_K_M.gguf new file mode 100644 index 0000000..f92251b --- /dev/null +++ b/GRLHF-2B-Pretrained.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1325d263fa67b5073726f428ae8377031961ec3c7163cfc73c393ae4d8161585 +size 1285493312 diff --git a/GRLHF-2B-Pretrained.Q5_K_S.gguf b/GRLHF-2B-Pretrained.Q5_K_S.gguf new file mode 100644 index 0000000..c706acc --- /dev/null +++ b/GRLHF-2B-Pretrained.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f574f594d26eae6fe7176d3e62ecb9975250e96ee1edb3370876cb0bcb50dd +size 1259172416 diff --git a/GRLHF-2B-Pretrained.Q6_K.gguf b/GRLHF-2B-Pretrained.Q6_K.gguf new file mode 100644 index 0000000..33686c4 --- /dev/null +++ b/GRLHF-2B-Pretrained.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df002c93399a673d4f3855bf0f80d3af8a57038a9739da0b1f4fca35f007a17 +size 1464177728 diff --git a/GRLHF-2B-Pretrained.Q8_0.gguf b/GRLHF-2B-Pretrained.Q8_0.gguf new file mode 100644 index 0000000..81463f8 --- /dev/null +++ b/GRLHF-2B-Pretrained.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321e24f386f141a3dbb013d4b350321e57003c31a6325d92fb7bb4f40b3aa2ff +size 1894531136 diff --git a/GRLHF-2B-Pretrained.f16.gguf b/GRLHF-2B-Pretrained.f16.gguf new file mode 100644 index 0000000..c01461e --- /dev/null +++ b/GRLHF-2B-Pretrained.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e326f1f22842f9827c0c7dccbfcf13c5dac09c717c36f263b755a9dc21b9f143 +size 3560415296 diff --git a/GRLHF-2B-Pretrained.mmproj-Q8_0.gguf b/GRLHF-2B-Pretrained.mmproj-Q8_0.gguf new file mode 100644 index 0000000..972be55 --- /dev/null +++ b/GRLHF-2B-Pretrained.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8d5c495508349f7108ea47b62fb67ef712cacf9974ba120b9f53e93a0345c7 +size 709882944 diff --git a/GRLHF-2B-Pretrained.mmproj-f16.gguf b/GRLHF-2B-Pretrained.mmproj-f16.gguf new file mode 100644 index 0000000..2364619 --- /dev/null +++ b/GRLHF-2B-Pretrained.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56618734d29fb5786a385b4bc8b469a1276039fafd6bddff95cb3455a38fe300 +size 1331655744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2a4ad89 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: generative-rlhf-v/GRLHF-2B-Pretrained +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/generative-rlhf-v/GRLHF-2B-Pretrained + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRLHF-2B-Pretrained-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/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-2B-Pretrained-GGUF/resolve/main/GRLHF-2B-Pretrained.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. + +