commit ad6d3ced6b699ccaa7f68ca6fd409ca0b102f76b Author: ModelHub XC Date: Mon Apr 13 09:52:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-DeluXeOne-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..242b0a2 --- /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-DeluXeOne-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-DeluXeOne-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-DeluXeOne-8B.IQ4_XS.gguf b/Llama3.1-DeluXeOne-8B.IQ4_XS.gguf new file mode 100644 index 0000000..1bb6908 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97faabfd36d92bea00a60ab3cdd24a624e8d2f92721cd12d1d5cec66c0c102a +size 4484368160 diff --git a/Llama3.1-DeluXeOne-8B.Q2_K.gguf b/Llama3.1-DeluXeOne-8B.Q2_K.gguf new file mode 100644 index 0000000..f53f77b --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4ed89649777a5f3bc22abbd43a5bc38cc875a5bd62c811fbf948e3cebc70ed +size 3179136800 diff --git a/Llama3.1-DeluXeOne-8B.Q3_K_L.gguf b/Llama3.1-DeluXeOne-8B.Q3_K_L.gguf new file mode 100644 index 0000000..90158d2 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a75b2b3ff6b3847f23cdaa708d8eb98532619caaeebd8cbdf970c1987b6abf1f +size 4321961760 diff --git a/Llama3.1-DeluXeOne-8B.Q3_K_M.gguf b/Llama3.1-DeluXeOne-8B.Q3_K_M.gguf new file mode 100644 index 0000000..35306b9 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520ea2623a72934fa798cc8db8c1de260a974d1066109f4c06c933b642e9ef57 +size 4018923296 diff --git a/Llama3.1-DeluXeOne-8B.Q3_K_S.gguf b/Llama3.1-DeluXeOne-8B.Q3_K_S.gguf new file mode 100644 index 0000000..8103aeb --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9260c2290cf4f206826e3d907190945b7a0fd8bc9cb79054fe8ebe609580dd34 +size 3664504608 diff --git a/Llama3.1-DeluXeOne-8B.Q4_K_M.gguf b/Llama3.1-DeluXeOne-8B.Q4_K_M.gguf new file mode 100644 index 0000000..bc8604f --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcd35e8caeb8a54a1cfa6d4c59094ba58143b7660c24d6792cfa0aae68fd4b5 +size 4920739616 diff --git a/Llama3.1-DeluXeOne-8B.Q4_K_S.gguf b/Llama3.1-DeluXeOne-8B.Q4_K_S.gguf new file mode 100644 index 0000000..0890963 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68956e19498882c3f2e0e1e631d96540e93b13e9aa22442fc28b9520684c4569 +size 4692674336 diff --git a/Llama3.1-DeluXeOne-8B.Q5_K_M.gguf b/Llama3.1-DeluXeOne-8B.Q5_K_M.gguf new file mode 100644 index 0000000..f78622e --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf8efae99659febf73ca3e00d29d132ca1d1c65fb74aa6dbc1e94541d5cfbb8 +size 5732992800 diff --git a/Llama3.1-DeluXeOne-8B.Q5_K_S.gguf b/Llama3.1-DeluXeOne-8B.Q5_K_S.gguf new file mode 100644 index 0000000..1af7b28 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0c733e78dee4a7f4a7eda213bb5099963fd81a3fe95cca420a4cccd43e45a4 +size 5599299360 diff --git a/Llama3.1-DeluXeOne-8B.Q6_K.gguf b/Llama3.1-DeluXeOne-8B.Q6_K.gguf new file mode 100644 index 0000000..56f4ea6 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:515dc0a7248bc14d97e9c112fd3f3c141ad26e4286f32c38b44184e5b0811478 +size 6596011808 diff --git a/Llama3.1-DeluXeOne-8B.Q8_0.gguf b/Llama3.1-DeluXeOne-8B.Q8_0.gguf new file mode 100644 index 0000000..6f4ac7a --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2f784be581eefc3d0d2c4aaeef9924991b4aa47cff7ffb524900875c2eec84 +size 8540776224 diff --git a/Llama3.1-DeluXeOne-8B.f16.gguf b/Llama3.1-DeluXeOne-8B.f16.gguf new file mode 100644 index 0000000..2874419 --- /dev/null +++ b/Llama3.1-DeluXeOne-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a7083a0e835378afb8d4d0054ba9c793d726bf79566cc11a87e0a020be2516 +size 16068896544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d2d45bf --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Yuma42/Llama3.1-DeluXeOne-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- dphn/Dolphin-X1-8B +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yuma42/Llama3.1-DeluXeOne-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-DeluXeOne-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-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/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-DeluXeOne-8B-GGUF/resolve/main/Llama3.1-DeluXeOne-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. + +