commit fa6ee9a978b10d9af1cf5e1132753f9fbf13db25 Author: ModelHub XC Date: Sun May 31 02:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5454986 --- /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-gen-dpo-10k-beta0.8-lr5e-7.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.IQ4_XS.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.IQ4_XS.gguf new file mode 100644 index 0000000..9adc46e --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b344309bdc8afcd93ba8e8226455398660e10317a107dfa5e4124737dbcc20 +size 4484364192 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q2_K.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q2_K.gguf new file mode 100644 index 0000000..99db770 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5881a34b16e801a5ae955d4b2d3399a304482de9391899dc25aa30ce781730ba +size 3179132832 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_L.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_L.gguf new file mode 100644 index 0000000..6e82178 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570a4049f0d45216c459e4b4bab397b2a2721eb2e9bf48b3e4bc7805358921f6 +size 4321957792 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_M.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_M.gguf new file mode 100644 index 0000000..ef3e656 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90970a074f0ffa417f452f50dd54a1f633f2218ac7c3084c7790bdbd75e64911 +size 4018919328 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_S.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_S.gguf new file mode 100644 index 0000000..6cb5835 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15daa9550e45e88d421d5bef9aae6aab0ad4789a9633fc3a4e7a5a86a406dd91 +size 3664500640 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_M.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_M.gguf new file mode 100644 index 0000000..04f2146 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8b95a83f486e0b52bfcc28e965b825fbe4b30f1079ce740acd966ac567cd98 +size 4920735648 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_S.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_S.gguf new file mode 100644 index 0000000..05cd2f4 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cccf2815e5c635a3dab37280706bec914bdc7c425a5451df194769ae24737de +size 4692670368 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_M.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_M.gguf new file mode 100644 index 0000000..0b7a536 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e2ed0d3facf5fbb333e5c2ab5cb422e183d252620e44d4fa5bf227cc0caee9 +size 5732988832 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_S.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_S.gguf new file mode 100644 index 0000000..1e1b017 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54a5c109a34268a984d37f34b0a006a9e3dbecc7fc43371ef9e4d6d05d31a24 +size 5599295392 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q6_K.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q6_K.gguf new file mode 100644 index 0000000..f02454e --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79bf25e239bb48ab88db3cb69a78a9529687d25933be19906117465b4f7cc43e +size 6596007840 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q8_0.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q8_0.gguf new file mode 100644 index 0000000..8b7d215 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff6f687d91f048a0eacc198c4f3e4b8ccdc26f4b0661fd7a0bb1627ee8469dd +size 8540772256 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.f16.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.f16.gguf new file mode 100644 index 0000000..8566a5d --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ee34b81301fd6107bb8ea7444317e4617adc083f47429664c5f4c2f5606d0f +size 16068892576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc884e6 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7 +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-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-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-beta0.8-lr5e-7.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. + +