commit 1cfc058796535f5515e046d5f99122c6c22e3890 Author: ModelHub XC Date: Mon Jun 1 17:50:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b786a8 --- /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-3.1-8B-sft-dpo-10k-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.IQ4_XS.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..97b0f15 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79575ee84b3c852268c2bc520d95795235692ad283b6f88b37c241a08b6b0551 +size 4484364128 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q2_K.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q2_K.gguf new file mode 100644 index 0000000..bc1695a --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999b342ebedfbf0093db205b7e7a58cf625c1beface9d39427bd28c635dd9320 +size 3179132768 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_L.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..9dd1701 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3e7e773ab69149e2e0dc59ad7a658fb3c888278f960b32354d7f98fbaeeee4 +size 4321957728 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_M.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..ebb9b7a --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ab733ea0632aec8497db24f24cf93da4f06d13e8864714f221e60ce0d6fa75 +size 4018919264 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_S.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..46d96f5 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7214cc6b108195c901080fdc07dda9ada32fcb5544d57d64905f51bd8cfa0714 +size 3664500576 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_M.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..c20f2b2 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04edb4577f87816329fbf46f88d1f6513ecd7e315a327ab185598bc17e6a019c +size 4920735584 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_S.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..a0ce391 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03d059faa390d3fbfde444d68cb233e05acec3cc6fd3d29bfb035792e7e79f8 +size 4692670304 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_M.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..b0de4a3 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613b7ab4c1f235dfb90c3bf4c78d346862bd36e16208270fb47ff7d7a9711fd6 +size 5732988768 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_S.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..3fba851 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9671a996944dfdd6358a3fe037f24cf4830abf43c3adb3726f1899be6f0eb4 +size 5599295328 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q6_K.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q6_K.gguf new file mode 100644 index 0000000..31bf8ca --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e212a408238842bdc40626cd88c412ed23de82265d6f933a81e95f970b233e +size 6596007776 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.Q8_0.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q8_0.gguf new file mode 100644 index 0000000..64e1197 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78cc6f78ea2f328fbd8fb058d765b4408e908e18a36aa45d9515efcaf0aba1b1 +size 8540772192 diff --git a/Llama-3.1-8B-sft-dpo-10k-ORPO.f16.gguf b/Llama-3.1-8B-sft-dpo-10k-ORPO.f16.gguf new file mode 100644 index 0000000..d4dd898 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6c205a0a8a16967f6d13e5376b94cbb63bbb8772ba3cb64eaa043f7ef18efb +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca1d468 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-dpo-10k-ORPO +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-dpo-10k-ORPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- orpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-dpo-10k-ORPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-sft-dpo-10k-ORPO-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-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-ORPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-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. + +