commit 28ed51a4607b6f4191d27dc8bf1138e4227be8c5 Author: ModelHub XC Date: Sat Jun 13 08:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRLHF-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ff9a69a --- /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-3B-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRLHF-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRLHF-3B-Instruct.IQ4_XS.gguf b/GRLHF-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..0b97968 --- /dev/null +++ b/GRLHF-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294aa80b881b03de493a8b80895d17b365ded680f8c261a834e03cd8368d5c06 +size 1918490080 diff --git a/GRLHF-3B-Instruct.Q2_K.gguf b/GRLHF-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..25e7e59 --- /dev/null +++ b/GRLHF-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdecda208c6d609b84051fcebb21db829461fd5d62b906b90d666d59ae24f834 +size 1376855520 diff --git a/GRLHF-3B-Instruct.Q3_K_L.gguf b/GRLHF-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6b0a364 --- /dev/null +++ b/GRLHF-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6656028d74f2d57764f342db1ba1ba2be5622ac0c94cb9a63f304cce69f391b +size 1841094112 diff --git a/GRLHF-3B-Instruct.Q3_K_M.gguf b/GRLHF-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..3d579d8 --- /dev/null +++ b/GRLHF-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beabc46f7e773102e3dcf3e291b99d94d4477483abe820bbe981fd6f80969d34 +size 1724177888 diff --git a/GRLHF-3B-Instruct.Q3_K_S.gguf b/GRLHF-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..3cf6eb3 --- /dev/null +++ b/GRLHF-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e3ac5383e7036cef0ebdb7ffa37f0ecbe462519cf9bbc653a644f70d0d0a4d +size 1588059616 diff --git a/GRLHF-3B-Instruct.Q4_K_M.gguf b/GRLHF-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..9001a53 --- /dev/null +++ b/GRLHF-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69bf1754f04d6e6b1b7a362a45de645bcad2aad9137e6eba8756065fcfdb37c +size 2104931808 diff --git a/GRLHF-3B-Instruct.Q4_K_S.gguf b/GRLHF-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..4297bc2 --- /dev/null +++ b/GRLHF-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eeb7e50143539f4cf48653634a43332e2ad9c568539bd74ad6edff69e37193e +size 2009413088 diff --git a/GRLHF-3B-Instruct.Q5_K_M.gguf b/GRLHF-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..83fccf5 --- /dev/null +++ b/GRLHF-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:977bf3304255d26f42556f8c4d4291df1642e496c87f7e99c506f39acfd19c65 +size 2438739424 diff --git a/GRLHF-3B-Instruct.Q5_K_S.gguf b/GRLHF-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..b3e6b43 --- /dev/null +++ b/GRLHF-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e43de747d50a0b0d91696f84824cb94f7e2683b38070edea07002b4b5e7f6c +size 2383590880 diff --git a/GRLHF-3B-Instruct.Q6_K.gguf b/GRLHF-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..94eee3a --- /dev/null +++ b/GRLHF-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e729ef57653a0c68f2101cf939a23393ea34a158f9e32d9d441d365f629cd3c +size 2793410016 diff --git a/GRLHF-3B-Instruct.Q8_0.gguf b/GRLHF-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a3062f2 --- /dev/null +++ b/GRLHF-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82fb253ef201966afafb783126af915e29075e2464b91b137cb97ed05c180ee9 +size 3616087520 diff --git a/GRLHF-3B-Instruct.f16.gguf b/GRLHF-3B-Instruct.f16.gguf new file mode 100644 index 0000000..af25298 --- /dev/null +++ b/GRLHF-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9365be921e3df1b9d2c8dd31faddf9a8787f7e4dbca69c0704ab6bddaec3e02 +size 6800645600 diff --git a/GRLHF-3B-Instruct.mmproj-Q8_0.gguf b/GRLHF-3B-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..1188d52 --- /dev/null +++ b/GRLHF-3B-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026fafacac44da797991769b5159a001b2f462177f144cf73031bfef0e986e3d +size 844757696 diff --git a/GRLHF-3B-Instruct.mmproj-f16.gguf b/GRLHF-3B-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..c2c2df2 --- /dev/null +++ b/GRLHF-3B-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5d9ade68614baee4e3f517f7a86fb64890c9f0a02667621d9269da2f277cc7 +size 1338428096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3ad9cc --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: generative-rlhf-v/GRLHF-3B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/generative-rlhf-v/GRLHF-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRLHF-3B-Instruct-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-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRLHF-3B-Instruct-GGUF/resolve/main/GRLHF-3B-Instruct.f16.gguf) | f16 | 6.9 | 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. + +