commit 84b4f4cbec6c7faaa2fd0d74afb7dd9f20088c77 Author: ModelHub XC Date: Tue Sep 29 08:29:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-ORPO-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8a3852 --- /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 +Llama-3-8B-ORPO-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ORPO-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-ORPO-V1.IQ4_XS.gguf b/Llama-3-8B-ORPO-V1.IQ4_XS.gguf new file mode 100644 index 0000000..f5b5495 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fffc6942b47bd0410c7461c2d618ba48cec80a048d5e59baa4d3d2b25df8055 +size 4484374240 diff --git a/Llama-3-8B-ORPO-V1.Q2_K.gguf b/Llama-3-8B-ORPO-V1.Q2_K.gguf new file mode 100644 index 0000000..65f3a40 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed2ce655213a30456ecc31acd81ba61a929ac0fd94d92682499fc3e7dd374cc +size 3179141216 diff --git a/Llama-3-8B-ORPO-V1.Q3_K_L.gguf b/Llama-3-8B-ORPO-V1.Q3_K_L.gguf new file mode 100644 index 0000000..284f00b --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1294e7f2755e16547b4fc800646d6fddf8bc6e090383fc8d2bbf83369c371a85 +size 4321967008 diff --git a/Llama-3-8B-ORPO-V1.Q3_K_M.gguf b/Llama-3-8B-ORPO-V1.Q3_K_M.gguf new file mode 100644 index 0000000..3cca5ab --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27377e727f6013d24d112c7eb8746614a850cb2ce37f36c731a2a43d73288152 +size 4018928544 diff --git a/Llama-3-8B-ORPO-V1.Q3_K_S.gguf b/Llama-3-8B-ORPO-V1.Q3_K_S.gguf new file mode 100644 index 0000000..deba102 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4829cc39f386c5ef6fb285c646d98422c8a4db6ca981e21d59cb212bf6a6ddd +size 3664509856 diff --git a/Llama-3-8B-ORPO-V1.Q4_K_M.gguf b/Llama-3-8B-ORPO-V1.Q4_K_M.gguf new file mode 100644 index 0000000..c37079d --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9140bedd357a9cdd49039c34d405a46b58fd2e1d9bb910993e52962c32310c +size 4920745952 diff --git a/Llama-3-8B-ORPO-V1.Q4_K_S.gguf b/Llama-3-8B-ORPO-V1.Q4_K_S.gguf new file mode 100644 index 0000000..497a049 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b983cfa32ecd88f4a3fec669982da5179021a7b962d413663a45a2eb2fffb13d +size 4692680672 diff --git a/Llama-3-8B-ORPO-V1.Q5_K_M.gguf b/Llama-3-8B-ORPO-V1.Q5_K_M.gguf new file mode 100644 index 0000000..6e4f76c --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83f10f0a5690a046410304096e11fdf4f3d430f310656f205a7fb49c8a81280 +size 5733000160 diff --git a/Llama-3-8B-ORPO-V1.Q5_K_S.gguf b/Llama-3-8B-ORPO-V1.Q5_K_S.gguf new file mode 100644 index 0000000..8d7378e --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581faa34eb3afd91ac678d5983744ba1e5906a46c01ad8d5d9ef38096ce57c94 +size 5599306720 diff --git a/Llama-3-8B-ORPO-V1.Q6_K.gguf b/Llama-3-8B-ORPO-V1.Q6_K.gguf new file mode 100644 index 0000000..436a043 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cad9431d6a285c0a92106a44668ee39a9c88091bec16b331411c263535f8bf1 +size 6596020256 diff --git a/Llama-3-8B-ORPO-V1.Q8_0.gguf b/Llama-3-8B-ORPO-V1.Q8_0.gguf new file mode 100644 index 0000000..1840ce3 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721f7929c7cb7f9f25708f66d2949c135b24784d74c10f60cffcfec434d818df +size 8540788640 diff --git a/Llama-3-8B-ORPO-V1.f16.gguf b/Llama-3-8B-ORPO-V1.f16.gguf new file mode 100644 index 0000000..9822233 --- /dev/null +++ b/Llama-3-8B-ORPO-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762fd358fc488190dad84d3c3073ef4cdcc5d629db43a10dcd597c48aa896c9a +size 16068924320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ba27406 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Z3R6X/Llama-3-8B-ORPO-V1 +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Z3R6X/Llama-3-8B-ORPO-V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-ORPO-V1-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/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ORPO-V1-GGUF/resolve/main/Llama-3-8B-ORPO-V1.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. + +