commit 19dd2518aedc78d7b1d2fc783bb76d78fffd681e Author: ModelHub XC Date: Tue May 26 10:10:19 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-KTO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e4f63b --- /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-KTO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-all-pool-KTO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-all-pool-KTO.IQ4_XS.gguf b/Llama-3.1-8B-sft-all-pool-KTO.IQ4_XS.gguf new file mode 100644 index 0000000..f495ea1 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513cba859b8037e95a4359dfa2b85403d54c0fb686b55e7d9f6e9ae27e02434d +size 4484364128 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q2_K.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q2_K.gguf new file mode 100644 index 0000000..b9d25fb --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a982112ce841de9adb671b428cdd381ba2282feca3daf048277fca8963b3ae33 +size 3179132768 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_L.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_L.gguf new file mode 100644 index 0000000..89c9ca6 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bc100434493cd8a50ff7c1f5176a09106573d8e7b3e0eae67b61988be1b8f2 +size 4321957728 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_M.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_M.gguf new file mode 100644 index 0000000..d471d48 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23d7a223eaefa364dcfe34ff5672eb4f561c9c9a03917da89cf07fdf42a3c96 +size 4018919264 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_S.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_S.gguf new file mode 100644 index 0000000..c31d49e --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1435ff798d5e7d860f8e2d26d9870c1faaff80de32ff3c59af71fea50a61bc9e +size 3664500576 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_M.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_M.gguf new file mode 100644 index 0000000..ddee0a8 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b608b8cdd983859011da3ed09f082be84b1619d80a182c1c22704f822fd74d +size 4920735584 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_S.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_S.gguf new file mode 100644 index 0000000..06fac90 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9df1c5208e4254879774f6d4a7dfb2d263d668ef8ce8f3bf3bc2fd9da342ce +size 4692670304 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_M.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_M.gguf new file mode 100644 index 0000000..d79a90c --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4c28245d4be206839bd641f322dc61b2dbb4c752f11d577f1aca9832850eb3 +size 5732988768 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_S.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_S.gguf new file mode 100644 index 0000000..853a0ae --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41afe4661cdbc8f633e424030fd1a6ae7b56e313e9c1450de9a4501f6d9fa17 +size 5599295328 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q6_K.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q6_K.gguf new file mode 100644 index 0000000..f5986ea --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4518ee227de903ee74e657d351480b547b3b05d54af3b51f1accd772f84aece6 +size 6596007776 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.Q8_0.gguf b/Llama-3.1-8B-sft-all-pool-KTO.Q8_0.gguf new file mode 100644 index 0000000..4ce5166 --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a8929112f6bec3225b9e32471ab89160921871c7e3dfadbde3dbba7a99af7e +size 8540772192 diff --git a/Llama-3.1-8B-sft-all-pool-KTO.f16.gguf b/Llama-3.1-8B-sft-all-pool-KTO.f16.gguf new file mode 100644 index 0000000..c32e1cb --- /dev/null +++ b/Llama-3.1-8B-sft-all-pool-KTO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51fb7e4d9de8a965e3c55761564f5cc8572110e499fbd576d429cd33dd860f04 +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1ced429 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-all-pool-KTO +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-all-pool-KTO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- kto +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-all-pool-KTO + + + +***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-KTO-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-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-all-pool-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-all-pool-KTO.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. + +