commit 2873b3d235194333ca9bd0db3af7dddd19ebc8f7 Author: ModelHub XC Date: Mon Jun 15 05:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37c7672 --- /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 +Llama-3-8B-Instruct-UltraDPO3-NT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO3-NT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_M.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_M.gguf new file mode 100644 index 0000000..8efa06c --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da38cce63f0e51c7944f3ab93e0b6f3e8a5e0679507366363aad87901a4636a +size 3784823616 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_S.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_S.gguf new file mode 100644 index 0000000..b8912d6 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c964557e69c024bcd63eb1a4ea8d72f5b98b38a817171c83ee6967e3bf61d707 +size 3682325312 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_XS.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_XS.gguf new file mode 100644 index 0000000..6256293 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e66f085a0259fcad95db1b02a108c229c351b735b1ce8b6b492027dfaf8fd3 +size 3518747456 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.IQ4_XS.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ4_XS.gguf new file mode 100644 index 0000000..837297c --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca571c193d5b087f7c0606496347e0fd0290c35937dcfdb8020123e94cb84e5 +size 4484363072 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q2_K.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q2_K.gguf new file mode 100644 index 0000000..fac0b2c --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd4ed060fee0613bcd3119ec40156011c6e24789e728fac107151bea2b77fd3 +size 3179131712 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_L.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_L.gguf new file mode 100644 index 0000000..187c780 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dafa442c11ab9420d15d62375a0da1570b0f118a0b7962a8da4cc906dfa07da8 +size 4321956672 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_M.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_M.gguf new file mode 100644 index 0000000..b991800 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddafc8e57fdc200b9cb132a2e25c26d30bb989e9e3e494617732dccb415abe62 +size 4018918208 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_S.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_S.gguf new file mode 100644 index 0000000..eb07ebf --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c51ded823f1cf0a2d18d49b090287769938afc6a526d3956da19f07908e062 +size 3664499520 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_M.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_M.gguf new file mode 100644 index 0000000..ff76c0d --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb071ddffdda9754538e9ab02b9d4367cd062f0f931689962a0c6ddf2a67cc9d +size 4920734528 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_S.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_S.gguf new file mode 100644 index 0000000..72a09ae --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3b27712895920a72ada8acd240ba53c6a96b8f92fd256f1c1f3f5011c12e6f +size 4692669248 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_M.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_M.gguf new file mode 100644 index 0000000..b4cfc49 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f9acb7c88f87e598f73583b86bb21656379e49e19a04effce92bc63b34dbd7 +size 5732987712 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_S.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_S.gguf new file mode 100644 index 0000000..e361af8 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741017692b5b0e1243baac4b783394d19c416a8e9b7f60496a1d64b0db304514 +size 5599294272 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q6_K.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q6_K.gguf new file mode 100644 index 0000000..1950123 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6b4450464b5e4ade54c2f13d64fdb6f21a400ceb8532c226639cb305327401 +size 6596006720 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.Q8_0.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.Q8_0.gguf new file mode 100644 index 0000000..6429429 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b7677d3e1cb0acb0f0777d57a3c0fffbe9ddafd3a2eae820b918e0aaf45601 +size 8540771136 diff --git a/Llama-3-8B-Instruct-UltraDPO3-NT.f16.gguf b/Llama-3-8B-Instruct-UltraDPO3-NT.f16.gguf new file mode 100644 index 0000000..8f38049 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO3-NT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc343f4966c444a371d9d1fd28e48f121f91646f4c5c55d1aebebdfd3765132f +size 16068891456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa72fb7 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Magpie-Align/Llama-3-8B-Instruct-UltraDPO3-NT +datasets: +- princeton-nlp/llama3-ultrafeedback +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- alignment-handbook +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Magpie-Align/Llama-3-8B-Instruct-UltraDPO3-NT + + +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-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO3-NT-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO3-NT.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. + +