commit 1b7112c1d9ec5d3b2e741be21be3d3b5f6dfcdf2 Author: ModelHub XC Date: Thu Jul 30 23:37:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ff1b7e --- /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-Instruct-DPO-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-DPO-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-DPO-v0.2.IQ4_XS.gguf b/Llama-3-8B-Instruct-DPO-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..720abd8 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d2f5fee46c7ff3f04f06b55b590c26517a00b578a908f147a9dbee37d23cb1 +size 4484369728 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q2_K.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q2_K.gguf new file mode 100644 index 0000000..ff9924d --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d38bada065b9ea29b418f1ce56ef60784320d3dead8c5518e92ced12e8f77f +size 3179137536 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_L.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..b0f3ec8 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e91acdbd57e485fd406046cc4284cb586bdd43eee49576227740e11466ba4a8 +size 4321962912 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_M.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..70e4507 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eacdecaa48e4969ad38ab556b2b545e33fc3d24eda44187ef64e6f5fba90ad4 +size 4018924448 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_S.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..7db5e44 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d1e05d5e361d380c5d1333238684e473c10df4368ca92b0e922cba037a7d46 +size 3664505760 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_M.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..4eaadd3 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1863f0ac58a4b8e34274ce1d87214ec15f7b57ca5b3e91c843f828bc226062 +size 4920741312 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_S.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..8dc9cee --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886bda304a9cf97d9fc6798b74e987504aa45d053657cd358792fc209c33265d +size 4692676032 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_M.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..e283fab --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a1496079e7edcfac77686f2d1a6f7e61633c12eb655eac107139f121500e05 +size 5732995008 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_S.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..8cce94b --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee43f2a223c286c2fb71c78f46aef9da82d512e97d6c0e2f36f8b7cd098fd97 +size 5599301568 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q6_K.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q6_K.gguf new file mode 100644 index 0000000..216c00d --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1fcf74bdabe5fecabf13ed9ab4e5923ba193ed231cdb3db81e426267ba1f556 +size 6596014560 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.Q8_0.gguf b/Llama-3-8B-Instruct-DPO-v0.2.Q8_0.gguf new file mode 100644 index 0000000..f424231 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07188e1ed3228e76466bc7646451a1f179fdb57fb4fc8598e87f2e1ac968c484 +size 8540780960 diff --git a/Llama-3-8B-Instruct-DPO-v0.2.f16.gguf b/Llama-3-8B-Instruct-DPO-v0.2.f16.gguf new file mode 100644 index 0000000..745aa20 --- /dev/null +++ b/Llama-3-8B-Instruct-DPO-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cdae7e6f414ec6c78b04f658472795f872fdf9f0a3582bc96ea82e939bb788 +size 16068908960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..edf3edf --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2 +datasets: +- argilla/ultrafeedback-binarized-preferences +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: llama3 +model_creator: MaziyarPanahi +model_name: Llama-3-8B-Instruct-DPO-v0.2 +quantized_by: mradermacher +tags: +- axolotl +- finetune +- dpo +- facebook +- meta +- pytorch +- llama +- llama-3 +--- +## About + + + + + + +static quants of https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-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/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-DPO-v0.2-GGUF/resolve/main/Llama-3-8B-Instruct-DPO-v0.2.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. + +