commit 92ecf7d3f0a9b9d1b0f20958534318515c96493e Author: ModelHub XC Date: Sun Jun 14 05:42:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/dpo-llama-3-1-8b-math-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0d8c30f --- /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 +dpo-llama-3-1-8b-math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.f16.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dpo-llama-3-1-8b-math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4e14948 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: philschmid/dpo-llama-3-1-8b-math +language: +- en +library_name: transformers +model_name: dpo-llama-3-1-8b-math +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/philschmid/dpo-llama-3-1-8b-math + + +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/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/dpo-llama-3-1-8b-math-GGUF/resolve/main/dpo-llama-3-1-8b-math.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/dpo-llama-3-1-8b-math.IQ4_XS.gguf b/dpo-llama-3-1-8b-math.IQ4_XS.gguf new file mode 100644 index 0000000..34353d1 --- /dev/null +++ b/dpo-llama-3-1-8b-math.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f76dc070fcd3b24f8f2457ac08134191bebbb24b8bc199805731ae39bc4a3e +size 4484368224 diff --git a/dpo-llama-3-1-8b-math.Q2_K.gguf b/dpo-llama-3-1-8b-math.Q2_K.gguf new file mode 100644 index 0000000..84aeb99 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ba38991111a4d338dfddd0230d745b1cf8ea92f668b6fc80ad3a5f858878b0 +size 3179136864 diff --git a/dpo-llama-3-1-8b-math.Q3_K_L.gguf b/dpo-llama-3-1-8b-math.Q3_K_L.gguf new file mode 100644 index 0000000..1b6b198 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a56a16a488b00585722de2f3fb4d4efc606d70c478c3f11494225c01747531b +size 4321961824 diff --git a/dpo-llama-3-1-8b-math.Q3_K_M.gguf b/dpo-llama-3-1-8b-math.Q3_K_M.gguf new file mode 100644 index 0000000..4359fed --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6fca4e0e365e43ee411e3166852c642b746b52fe20141347035cf80ee827b2 +size 4018923360 diff --git a/dpo-llama-3-1-8b-math.Q3_K_S.gguf b/dpo-llama-3-1-8b-math.Q3_K_S.gguf new file mode 100644 index 0000000..fde7eb0 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d7eb8237f08a96100477dde9b90eb5af3b76f8d733f74e9fd3aa03169fc461 +size 3664504672 diff --git a/dpo-llama-3-1-8b-math.Q4_K_M.gguf b/dpo-llama-3-1-8b-math.Q4_K_M.gguf new file mode 100644 index 0000000..fd290ac --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81111550b789d8150d2566a3ecd6d060860413114652dbde075b04945afbda48 +size 4920739680 diff --git a/dpo-llama-3-1-8b-math.Q4_K_S.gguf b/dpo-llama-3-1-8b-math.Q4_K_S.gguf new file mode 100644 index 0000000..84a39b0 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a681ca1f730841315b5930de1c29ae93df9fca43aafde4a97fefdf0fcd95c2f8 +size 4692674400 diff --git a/dpo-llama-3-1-8b-math.Q5_K_M.gguf b/dpo-llama-3-1-8b-math.Q5_K_M.gguf new file mode 100644 index 0000000..61e0d12 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214237e556e49d3a9c1d8202c6d171b4d49ef12f3b8fa37f3de719dd06cc74c8 +size 5732992864 diff --git a/dpo-llama-3-1-8b-math.Q5_K_S.gguf b/dpo-llama-3-1-8b-math.Q5_K_S.gguf new file mode 100644 index 0000000..43012fa --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69b6fc7e1057a5a9ec2e719dc2953190974263aa7c92e667217170e1fcf2a2b +size 5599299424 diff --git a/dpo-llama-3-1-8b-math.Q6_K.gguf b/dpo-llama-3-1-8b-math.Q6_K.gguf new file mode 100644 index 0000000..bfd7554 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0c6cc792906b0c56434185b190308b1451618666b000a279da30708edbccd7 +size 6596011872 diff --git a/dpo-llama-3-1-8b-math.Q8_0.gguf b/dpo-llama-3-1-8b-math.Q8_0.gguf new file mode 100644 index 0000000..ddafe07 --- /dev/null +++ b/dpo-llama-3-1-8b-math.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70f67d886990ca2a52336a1cc65a290f3a0592ab775355779c66e00ed46c2a7 +size 8540776288 diff --git a/dpo-llama-3-1-8b-math.f16.gguf b/dpo-llama-3-1-8b-math.f16.gguf new file mode 100644 index 0000000..e930d52 --- /dev/null +++ b/dpo-llama-3-1-8b-math.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a2ffd0811d036a18dbe0698183ffb6d9d2a5a9eea259b759d39b973b5c2eb46 +size 16068896608