commit 43e25cc2d3ca507c178734462da601aee145d6fe Author: ModelHub XC Date: Mon Jun 15 06:51:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FactAlign-LLaMA-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21f859a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +FactAlign-LLaMA-3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FactAlign-LLaMA-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FactAlign-LLaMA-3-8B.IQ3_M.gguf b/FactAlign-LLaMA-3-8B.IQ3_M.gguf new file mode 100644 index 0000000..bb3a8ac --- /dev/null +++ b/FactAlign-LLaMA-3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f223c046978a6a30904b1917171f7e15399aa7cbbb0a8791a4a37236f1a48722 +size 3784824320 diff --git a/FactAlign-LLaMA-3-8B.IQ3_S.gguf b/FactAlign-LLaMA-3-8B.IQ3_S.gguf new file mode 100644 index 0000000..78e6103 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e4ac8b7f83a8d612c8f97afc35517d764027f49485ed3597b6626c4c7a5926 +size 3682326016 diff --git a/FactAlign-LLaMA-3-8B.IQ3_XS.gguf b/FactAlign-LLaMA-3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..6801500 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d898c84450c1a6624feff2967c216bf096d0cff6b88d7dc1eb1284589f076f +size 3518748160 diff --git a/FactAlign-LLaMA-3-8B.IQ4_XS.gguf b/FactAlign-LLaMA-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..376c5be --- /dev/null +++ b/FactAlign-LLaMA-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9ac3bf0abc601472f0842f1e0f7ec43079db2ce3c65d1b37caffcfff1fd0a4 +size 4484363776 diff --git a/FactAlign-LLaMA-3-8B.Q2_K.gguf b/FactAlign-LLaMA-3-8B.Q2_K.gguf new file mode 100644 index 0000000..d0397d8 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b06e7f9344cea75bdb5d204585bf24410d2c16ae4645e9a85d647a10221eec8 +size 3179132416 diff --git a/FactAlign-LLaMA-3-8B.Q3_K_L.gguf b/FactAlign-LLaMA-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..e71e7ae --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5f25c1088687fa981f4ff72211348061801effd10ff26e2c0197849adf4bb6 +size 4321957376 diff --git a/FactAlign-LLaMA-3-8B.Q3_K_M.gguf b/FactAlign-LLaMA-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..a3ead4a --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e81ce6c863687328b337790413e420ad9f49cc53ea535aa57d0ca94e236c9b0 +size 4018918912 diff --git a/FactAlign-LLaMA-3-8B.Q3_K_S.gguf b/FactAlign-LLaMA-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..fea542e --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3e04c52d1d299863e3eeac3f5e73e49103bc0db4aa21cc692b223eaa639de5 +size 3664500224 diff --git a/FactAlign-LLaMA-3-8B.Q4_K_M.gguf b/FactAlign-LLaMA-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..40e4614 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae0e4ad0bef5a119df1af1e59a5b4ae2a548f47d904528012868f69c0355f0f +size 4920735232 diff --git a/FactAlign-LLaMA-3-8B.Q4_K_S.gguf b/FactAlign-LLaMA-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..1cb44cc --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93abc424423bd9cc203253ac8b0afbb7eca2aaf89df3d37745bad044004c6a00 +size 4692669952 diff --git a/FactAlign-LLaMA-3-8B.Q5_K_M.gguf b/FactAlign-LLaMA-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..a9eb242 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745499c8a666f63c7e1a347be733bb0d4a238669802c5eb5ecb0f3b51be6ee0e +size 5732988416 diff --git a/FactAlign-LLaMA-3-8B.Q5_K_S.gguf b/FactAlign-LLaMA-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..e4c3478 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d03c9f096c26a9bee13bc9b8c4c2cef341c7ebcb8171f04d720c91722d2cfe3 +size 5599294976 diff --git a/FactAlign-LLaMA-3-8B.Q6_K.gguf b/FactAlign-LLaMA-3-8B.Q6_K.gguf new file mode 100644 index 0000000..5620edd --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56385b70f2122c76e589a2f88bf196b6f7ac0394d3edaaabb13ae809a2c3015e +size 6596007424 diff --git a/FactAlign-LLaMA-3-8B.Q8_0.gguf b/FactAlign-LLaMA-3-8B.Q8_0.gguf new file mode 100644 index 0000000..d107a7a --- /dev/null +++ b/FactAlign-LLaMA-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c70e8d9d5856e505f547b5cfe7164d8851305436b613398f2ed08469cdc4024 +size 8540771840 diff --git a/FactAlign-LLaMA-3-8B.f16.gguf b/FactAlign-LLaMA-3-8B.f16.gguf new file mode 100644 index 0000000..505a8f3 --- /dev/null +++ b/FactAlign-LLaMA-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74a54cdf7aafb313abddb01d6c4c17fff501b8dbdae5350549ceb3673358576 +size 16068892160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9e53181 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: chaoweihuang/FactAlign-LLaMA-3-8B +datasets: +- trl-lib/kto-mix-14k +- chaoweihuang/lf-response-llama3-f1_100_0.8-fg0.5 +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alignment-handbook +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/chaoweihuang/FactAlign-LLaMA-3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FactAlign-LLaMA-3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-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/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FactAlign-LLaMA-3-8B-GGUF/resolve/main/FactAlign-LLaMA-3-8B.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. + +