commit f1b847986170708c9681dabd17a96199499bcc34 Author: ModelHub XC Date: Wed May 27 12:02:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74e83e2 --- /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-all-pool-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.IQ4_XS.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..45507aa --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18b0c43e4f9701af8607a3b796fd5e4aad3db7923f8f43818ec0854e6f93eeb +size 4484364128 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q2_K.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q2_K.gguf new file mode 100644 index 0000000..0c8ceb6 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf6e7b8296497368989500188100ad8bf84daea5ba91c35fbe2601d083c679f +size 3179132768 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_L.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..8be76bc --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0a65069b0481649c61b9db23076bea8b7ff263c72780aa54f256c3d2cad731 +size 4321957728 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_M.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..4154e63 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677a1848178dfb61dfbcd8585f4d5a225fa48223f719a60d77fb97f2b89490ef +size 4018919264 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_S.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..4e1b6c2 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9915df67d66a9f9862502aabf8f87ea689cf51a09df977e40cb03d1fe23a0b1 +size 3664500576 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_M.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..dc24702 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6111d3177c0b1a2ad44f021b469ae6c620957e11a0997bf8eceec859cf5805 +size 4920735584 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_S.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..3f3d183 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5a8ca06d831c8ef9e8c2fb60ffbe839db43966ed19d0f1ecfa8cf5a5da8a44 +size 4692670304 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_M.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..3f907fc --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d26f73d958e8d9e90a01f98d6706c7a38984aa1bbbfeb657d88da5630ec1f20e +size 5732988768 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_S.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..b4bc51b --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48f62ccbb644f18428dd1e42cb261ba92795f163bd786b0e904298a39a3efc5 +size 5599295328 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q6_K.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q6_K.gguf new file mode 100644 index 0000000..3c6e46e --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95eced8d06fe6b0493810383f2a742f2f5456f88271fa5f616cf5686ecfe3668 +size 6596007776 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.Q8_0.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.Q8_0.gguf new file mode 100644 index 0000000..cd1a013 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d12e94ee8276117550f112bd79fe5ca8e3b63f63e031ba768cc651029f17dc1 +size 8540772192 diff --git a/Llama-3.1-8B-sft-all-pool-ORPO.f16.gguf b/Llama-3.1-8B-sft-all-pool-ORPO.f16.gguf new file mode 100644 index 0000000..8c96c3c --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc51a29637d5f071951a674c2a7d2bc15a7c9da56da127f9fa4e6cef8e72c50 +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc26c76 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-all-pool-ORPO +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-all-pool-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-all-pool-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-all-pool-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-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-ORPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-ORPO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-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. + +