commit bf146ed026c49bf53ca8dae0be2e41eff680cfc6 Author: ModelHub XC Date: Sat Jun 13 23:57:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..852fe12 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +LLaMaRada-3-orpo-v2-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMaRada-3-orpo-v2-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMaRada-3-orpo-v2-8b.IQ3_M.gguf b/LLaMaRada-3-orpo-v2-8b.IQ3_M.gguf new file mode 100644 index 0000000..5ffd305 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8ac6a6fed97fb3777f8bddf8aefbc4eb4dd6f2c60dc999b333d9e02c9feab7 +size 3785346208 diff --git a/LLaMaRada-3-orpo-v2-8b.IQ3_S.gguf b/LLaMaRada-3-orpo-v2-8b.IQ3_S.gguf new file mode 100644 index 0000000..e33d050 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6321a39952ee0a95cf4f8d1e8d1191726e657c15f50f7b8ad8421c2525f7277 +size 3682847904 diff --git a/LLaMaRada-3-orpo-v2-8b.IQ3_XS.gguf b/LLaMaRada-3-orpo-v2-8b.IQ3_XS.gguf new file mode 100644 index 0000000..767e53c --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413e5d4e4f96ec699325aa7552fd3f0cab260af2c7b763e75acd603f14de2ad3 +size 3519270048 diff --git a/LLaMaRada-3-orpo-v2-8b.IQ4_XS.gguf b/LLaMaRada-3-orpo-v2-8b.IQ4_XS.gguf new file mode 100644 index 0000000..43c889f --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0149c5178ea009c00d1a612110411c1eb41afe126cc2e5d48d1d9947ce76a5 +size 4484886496 diff --git a/LLaMaRada-3-orpo-v2-8b.Q2_K.gguf b/LLaMaRada-3-orpo-v2-8b.Q2_K.gguf new file mode 100644 index 0000000..11cce49 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47e4f6c5b35fe3f94dbef7481815b71f24db950650f74d71eab48dde894ed45 +size 3179653472 diff --git a/LLaMaRada-3-orpo-v2-8b.Q3_K_L.gguf b/LLaMaRada-3-orpo-v2-8b.Q3_K_L.gguf new file mode 100644 index 0000000..a8eae45 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7abe225bb9a7dbff559a9d0376a60979c33984e3e30ab0ca03184f94d195a84 +size 4322479264 diff --git a/LLaMaRada-3-orpo-v2-8b.Q3_K_M.gguf b/LLaMaRada-3-orpo-v2-8b.Q3_K_M.gguf new file mode 100644 index 0000000..c3d351e --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b2c577541b479095a622c241d8b3635130ed19e04d4ad8252b846334510d61 +size 4019440800 diff --git a/LLaMaRada-3-orpo-v2-8b.Q3_K_S.gguf b/LLaMaRada-3-orpo-v2-8b.Q3_K_S.gguf new file mode 100644 index 0000000..aa7884a --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccb429ee5f37307c56ddeb9f12a28b09c47066e0c41aa0d8f568ec87bd74d38 +size 3665022112 diff --git a/LLaMaRada-3-orpo-v2-8b.Q4_K_M.gguf b/LLaMaRada-3-orpo-v2-8b.Q4_K_M.gguf new file mode 100644 index 0000000..7c04f18 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af7e3cb53731609194feeb4074425956034d4467120801e777ce6944be8a8ec +size 4921258208 diff --git a/LLaMaRada-3-orpo-v2-8b.Q4_K_S.gguf b/LLaMaRada-3-orpo-v2-8b.Q4_K_S.gguf new file mode 100644 index 0000000..b0deeeb --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0647b19b765c226285c72d71683430b764f68c5b7863caa9bef7cbade4b6351c +size 4693192928 diff --git a/LLaMaRada-3-orpo-v2-8b.Q5_K_M.gguf b/LLaMaRada-3-orpo-v2-8b.Q5_K_M.gguf new file mode 100644 index 0000000..d1c6d7a --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1971a8b22bd109c96c657acac591738470a210ce1151ea76c6e44e98e0d5eec6 +size 5733512416 diff --git a/LLaMaRada-3-orpo-v2-8b.Q5_K_S.gguf b/LLaMaRada-3-orpo-v2-8b.Q5_K_S.gguf new file mode 100644 index 0000000..6a12b41 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95107f4ec9b9143dfc81ab8cea563a57dc1c0760b9bec0638893c374d18683f +size 5599818976 diff --git a/LLaMaRada-3-orpo-v2-8b.Q6_K.gguf b/LLaMaRada-3-orpo-v2-8b.Q6_K.gguf new file mode 100644 index 0000000..d16d015 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2487440efd86cf9e7ab35e5024eedb2002d5eb925a8d9d747e08f65ffa5f721d +size 6596532512 diff --git a/LLaMaRada-3-orpo-v2-8b.Q8_0.gguf b/LLaMaRada-3-orpo-v2-8b.Q8_0.gguf new file mode 100644 index 0000000..93a8a35 --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb73aae550402b63a97c77df6d9cca45d0d3b1ae2e10f034b100c741783b27b +size 8541300896 diff --git a/LLaMaRada-3-orpo-v2-8b.f16.gguf b/LLaMaRada-3-orpo-v2-8b.f16.gguf new file mode 100644 index 0000000..78016ef --- /dev/null +++ b/LLaMaRada-3-orpo-v2-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ffa276494e62c267e5deb99ba64b7ea76e44130be293eac86d342fe7a41c6b +size 16069436576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0db5435 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: BarraHome/LLaMaRada-3-orpo-v2-8b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/BarraHome/LLaMaRada-3-orpo-v2-8b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-i1-GGUF +## 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/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMaRada-3-orpo-v2-8b-GGUF/resolve/main/LLaMaRada-3-orpo-v2-8b.f16.gguf) | f16 | 16.2 | 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. + +