commit bacf28b8c109e24c3b3203d6602e9c9aa7ca04bc Author: ModelHub XC Date: Mon Jun 1 09:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralLlama-3-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ff52c02 --- /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 +NeuralLlama-3-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLlama-3-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralLlama-3-ORPO.IQ4_XS.gguf b/NeuralLlama-3-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..6d72003 --- /dev/null +++ b/NeuralLlama-3-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e92484f442672d1a3eba88521687e33830ebd19e42d968b103691e9c5062f71 +size 4484363296 diff --git a/NeuralLlama-3-ORPO.Q2_K.gguf b/NeuralLlama-3-ORPO.Q2_K.gguf new file mode 100644 index 0000000..a31a639 --- /dev/null +++ b/NeuralLlama-3-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f36af793254fb7c546d8a0795c17471ce95f6ed334aa3682d7e396f95bf5b68 +size 3179131936 diff --git a/NeuralLlama-3-ORPO.Q3_K_L.gguf b/NeuralLlama-3-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..e29ccb4 --- /dev/null +++ b/NeuralLlama-3-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce23cd93878673e638e85420259b768c042f90130acd23ec5223da13a445079 +size 4321956896 diff --git a/NeuralLlama-3-ORPO.Q3_K_M.gguf b/NeuralLlama-3-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..76f407f --- /dev/null +++ b/NeuralLlama-3-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b434edb76fc8307ca0ea91e5ebf70b0584ced19d2cebdcb442c00d56bda127be +size 4018918432 diff --git a/NeuralLlama-3-ORPO.Q3_K_S.gguf b/NeuralLlama-3-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..802490e --- /dev/null +++ b/NeuralLlama-3-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ed18b89c2e4f46285d616bfe5589716c3483a6cf9c92b965ef72636dab8624 +size 3664499744 diff --git a/NeuralLlama-3-ORPO.Q4_K_M.gguf b/NeuralLlama-3-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..1cc425e --- /dev/null +++ b/NeuralLlama-3-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffa965e0b788bfb3e403f0801ba859acd844e1737b9cd79546f921e17c7aa8b +size 4920734752 diff --git a/NeuralLlama-3-ORPO.Q4_K_S.gguf b/NeuralLlama-3-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..9db01a5 --- /dev/null +++ b/NeuralLlama-3-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8213c3d8ff42b55a0ea0a494d66023c2c232c8d3d2ef84e0e66192279b65ddf8 +size 4692669472 diff --git a/NeuralLlama-3-ORPO.Q5_K_M.gguf b/NeuralLlama-3-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..0e31f23 --- /dev/null +++ b/NeuralLlama-3-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6311128a212e006b7d35f06b9d40154258123476c0101684e2195ee90ad21b04 +size 5732987936 diff --git a/NeuralLlama-3-ORPO.Q5_K_S.gguf b/NeuralLlama-3-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..01492cc --- /dev/null +++ b/NeuralLlama-3-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf01b959a232c10bc4e228c7a0dccffa080bb12eb05e8a8667a6575241ff5f9 +size 5599294496 diff --git a/NeuralLlama-3-ORPO.Q6_K.gguf b/NeuralLlama-3-ORPO.Q6_K.gguf new file mode 100644 index 0000000..94cebaa --- /dev/null +++ b/NeuralLlama-3-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbfd6a95b75b5aa9fe451735948a9ce3e982ff6b70dc3d4d575c60f196657d30 +size 6596006944 diff --git a/NeuralLlama-3-ORPO.Q8_0.gguf b/NeuralLlama-3-ORPO.Q8_0.gguf new file mode 100644 index 0000000..4be8d4f --- /dev/null +++ b/NeuralLlama-3-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8c7d46fc21e97c608c0f56b891d853d34163208949d61b21a2e818ee41f5af +size 8540771360 diff --git a/NeuralLlama-3-ORPO.f16.gguf b/NeuralLlama-3-ORPO.f16.gguf new file mode 100644 index 0000000..d38d3c7 --- /dev/null +++ b/NeuralLlama-3-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a71ed088957a95131c3c86eb7e16bc7459b0e6963c7b28a3fd3882ebe74d5df +size 16068891680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..027a171 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: cookinai/NeuralLlama-3-ORPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- orpo +--- +## About + + + + + + +static quants of https://huggingface.co/cookinai/NeuralLlama-3-ORPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NeuralLlama-3-ORPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-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/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLlama-3-ORPO-GGUF/resolve/main/NeuralLlama-3-ORPO.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. + +