commit f26499313bf059a51235008c29aba90e509b0730 Author: ModelHub XC Date: Sun May 31 01:08:23 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-KTO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..041e654 --- /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-KTO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf new file mode 100644 index 0000000..14f64af --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a3bf62b761e71105c2ca1e55cebe6dedc09d9d5b4eb077f7506e9351ecf232 +size 4484364128 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q2_K.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q2_K.gguf new file mode 100644 index 0000000..15c614d --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e1ffcfa38fa0cb4887c2ae1faae0e33fb4d4d757920747538d9a548ef93934 +size 3179132768 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf new file mode 100644 index 0000000..d8e74be --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f82d6121fb84848406935dd07181d0b813c0d7afb3b47853cf2371d1c7db53c +size 4321957728 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf new file mode 100644 index 0000000..f9bf4bd --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541e1d5bfcc9a56fa140ca4e0c82d6abe4fa4ec6cfd3bf5152c267e6cee0755e +size 4018919264 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf new file mode 100644 index 0000000..04418d9 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7efc6d0a8844348bc628838f572d86079296ed88bd3b99d0ecb90d77fd1b04 +size 3664500576 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf new file mode 100644 index 0000000..6b52f9a --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc49b868089f89a5664bc052ea373d0be913b4cb9826f5b59bfb5daeab9b83c1 +size 4920735584 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf new file mode 100644 index 0000000..fdc3096 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d3babe4db1f2631aa066db89ad1e75788639b3742c517a5360d1e6604144ea +size 4692670304 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf new file mode 100644 index 0000000..97d25ce --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a98fda62fececf06319c329061ced66f5d3842b7d2bc7923f3729ae1ec7c952 +size 5732988768 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf new file mode 100644 index 0000000..6ccfdde --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa6165cf0fd556d6a9671b32fbb94fea713825c4bc3e7c76fb91e7cbb40591b +size 5599295328 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q6_K.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q6_K.gguf new file mode 100644 index 0000000..c1c5409 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042c0c2166cfdf204110ece5f2efd75b410eb4c4b8d3c85d0ecdaf6b58357909 +size 6596007776 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q8_0.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q8_0.gguf new file mode 100644 index 0000000..53df493 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69764d1335a0e8c3847fbe8274c01cdcd287e18d04a4559b2052038c44cc0b2 +size 8540772192 diff --git a/Llama-3.1-8B-sft-gen-dpo-10k-KTO.f16.gguf b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.f16.gguf new file mode 100644 index 0000000..cb5f758 --- /dev/null +++ b/Llama-3.1-8B-sft-gen-dpo-10k-KTO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb903b038d577948b05d4c764505e0f924c4230498329dcc8e91400b686caca +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ac6eb0a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-gen-dpo-10k-KTO +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-gen-dpo-10k-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-gen-dpo-10k-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-gen-dpo-10k-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-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-KTO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Llama-3.1-8B-sft-gen-dpo-10k-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. + +