commit 338fdccaec332f3aad80f7043c4b4d40f101be14 Author: ModelHub XC Date: Thu Jul 30 05:08:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Orpo-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..154c610 --- /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-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Orpo-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Orpo-v0.1.IQ4_XS.gguf b/Llama-3-8B-Orpo-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..6b5b243 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ac055840be583d47c1f4f9f47a96b0ceabfc2da2cacaff27c4691d1f6f2d0e +size 4484374880 diff --git a/Llama-3-8B-Orpo-v0.1.Q2_K.gguf b/Llama-3-8B-Orpo-v0.1.Q2_K.gguf new file mode 100644 index 0000000..a835fd5 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482f657fbcc68e40114b24c066254527dced5c37d84aa959cb8450307099f764 +size 3179141856 diff --git a/Llama-3-8B-Orpo-v0.1.Q3_K_L.gguf b/Llama-3-8B-Orpo-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..43aa37e --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba84ec26e82d251434ccfee44aac706fba51e4abcef5720803f0f7a2bb868c0 +size 4321967648 diff --git a/Llama-3-8B-Orpo-v0.1.Q3_K_M.gguf b/Llama-3-8B-Orpo-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..3122c94 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0bba0c3534b53cb1d28a6ad3d01953759defe22afa057087fb96d6b127c1d0 +size 4018929184 diff --git a/Llama-3-8B-Orpo-v0.1.Q3_K_S.gguf b/Llama-3-8B-Orpo-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..235a30d --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1831ead9bbc32c757af8714960de4357add16a71370d417fdd6ff9da8ea3687e +size 3664510496 diff --git a/Llama-3-8B-Orpo-v0.1.Q4_K_M.gguf b/Llama-3-8B-Orpo-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..2f2e751 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d9b946fc6be2382bae7e285fb9184dd95ee7e04d758f3d7b937540eac9b021 +size 4920746592 diff --git a/Llama-3-8B-Orpo-v0.1.Q4_K_S.gguf b/Llama-3-8B-Orpo-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..510ed53 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1710f11cc48dc542513f0886a5c013ca455534b4335b895d6ffbd38b9a13fc6d +size 4692681312 diff --git a/Llama-3-8B-Orpo-v0.1.Q5_K_M.gguf b/Llama-3-8B-Orpo-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..3fcd7ac --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e123105c54dd89150290303f1b18017cc4748ed31525ac703ab2c6df5fbb91 +size 5733000800 diff --git a/Llama-3-8B-Orpo-v0.1.Q5_K_S.gguf b/Llama-3-8B-Orpo-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..ab43d84 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e3299555dfb4b5e292a367a6fcd9da14bb48a9d62089cb780663731576dbc4 +size 5599307360 diff --git a/Llama-3-8B-Orpo-v0.1.Q6_K.gguf b/Llama-3-8B-Orpo-v0.1.Q6_K.gguf new file mode 100644 index 0000000..ec8ce84 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f83b93d5aa1996b122a420bcc3c9f32255d3e9e225303a2f1f4ccd222caa8e1 +size 6596020896 diff --git a/Llama-3-8B-Orpo-v0.1.Q8_0.gguf b/Llama-3-8B-Orpo-v0.1.Q8_0.gguf new file mode 100644 index 0000000..1d8689b --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c04d7147b3b3ca27935d0fbb86bebd91ccaea8b5c752c182f98928a22232804 +size 8540789280 diff --git a/Llama-3-8B-Orpo-v0.1.f16.gguf b/Llama-3-8B-Orpo-v0.1.f16.gguf new file mode 100644 index 0000000..3036120 --- /dev/null +++ b/Llama-3-8B-Orpo-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d098cdbe717ebf535da7d97e17cfcd2cbd96b538b090a4ca88770663125d59fa +size 16068924960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8816e5f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: dfurman/Llama-3-8B-Orpo-v0.1 +datasets: +- mlabonne/orpo-dpo-mix-40k +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- orpo +- llama 3 +- rlhf +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/dfurman/Llama-3-8B-Orpo-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-Orpo-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-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-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Orpo-v0.1-GGUF/resolve/main/Llama-3-8B-Orpo-v0.1.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. + +