commit 545fa66cb41344edbc6a2bffe3e6f181cb7d6a3e Author: ModelHub XC Date: Mon Aug 17 22:59:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b268211 --- /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 +Llama3.1-8B-NuminaMath-bridge.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-NuminaMath-bridge.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-NuminaMath-bridge.IQ4_XS.gguf b/Llama3.1-8B-NuminaMath-bridge.IQ4_XS.gguf new file mode 100644 index 0000000..0d3d10d --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d88d356ea3a1df5334f5dd01f512581e333fdcc0040b3465ff622c30d046015 +size 4484363840 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q2_K.gguf b/Llama3.1-8B-NuminaMath-bridge.Q2_K.gguf new file mode 100644 index 0000000..9bf95bb --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be484db3df4b8a111599d6c67bffe9fce1140272b00a0edc9efc03f7c6072d2 +size 3179132480 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q3_K_L.gguf b/Llama3.1-8B-NuminaMath-bridge.Q3_K_L.gguf new file mode 100644 index 0000000..0d22a60 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fc4bb09adb4f2b22ca4252572a3784fe334e393ea948cef633d29d526acc52 +size 4321957440 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q3_K_M.gguf b/Llama3.1-8B-NuminaMath-bridge.Q3_K_M.gguf new file mode 100644 index 0000000..ca10963 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875232191e6125d16a0a4857497a539af1c02cd478ccd7426bfe297c2d4c0968 +size 4018918976 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q3_K_S.gguf b/Llama3.1-8B-NuminaMath-bridge.Q3_K_S.gguf new file mode 100644 index 0000000..ecd005b --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b0bf6a5291f5fb2fc3331372d45344a9f8759cd8f3eb012e86cd125fc61b5a +size 3664500288 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q4_K_M.gguf b/Llama3.1-8B-NuminaMath-bridge.Q4_K_M.gguf new file mode 100644 index 0000000..22262dd --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ec63b53284f35a4f585a6e27688f34cbe54ceec2856873397ff5fd61fd0bca +size 4920735296 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q4_K_S.gguf b/Llama3.1-8B-NuminaMath-bridge.Q4_K_S.gguf new file mode 100644 index 0000000..b1a0358 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b01c2470053e2f8abb61b41ced64bbded7ab4e9865191441b888fa1ff3ac932 +size 4692670016 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q5_K_M.gguf b/Llama3.1-8B-NuminaMath-bridge.Q5_K_M.gguf new file mode 100644 index 0000000..62b4aaa --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942c625c590697d0aa65d5b7fd6762ea6d710cb3cf40a6175bcf7f97f5a299cd +size 5732988480 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q5_K_S.gguf b/Llama3.1-8B-NuminaMath-bridge.Q5_K_S.gguf new file mode 100644 index 0000000..df866b3 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ecbfca5357301feee960fb3622d49696e7015d6ee2b78088f42e619af073fd +size 5599295040 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q6_K.gguf b/Llama3.1-8B-NuminaMath-bridge.Q6_K.gguf new file mode 100644 index 0000000..dfb8172 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3fa37b8b825030c27faca8d4b6fe6aaf928750f1a08c5607ce75120982bfb52 +size 6596007488 diff --git a/Llama3.1-8B-NuminaMath-bridge.Q8_0.gguf b/Llama3.1-8B-NuminaMath-bridge.Q8_0.gguf new file mode 100644 index 0000000..c3232f1 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6600d739d3e82c07a0479748315012fc19d49e71d99ed0f3acde1062f74d83 +size 8540771904 diff --git a/Llama3.1-8B-NuminaMath-bridge.f16.gguf b/Llama3.1-8B-NuminaMath-bridge.f16.gguf new file mode 100644 index 0000000..86ef0f3 --- /dev/null +++ b/Llama3.1-8B-NuminaMath-bridge.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501168076f9f3cf6323e0014f73a28c1b6ebdaa8fc05b354c5bfc9678caf7b90 +size 16068892224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..212937b --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: zjuxhl/Llama3.1-8B-NuminaMath-bridge +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zjuxhl/Llama3.1-8B-NuminaMath-bridge + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-NuminaMath-bridge-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-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/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-NuminaMath-bridge-GGUF/resolve/main/Llama3.1-8B-NuminaMath-bridge.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. + +