commit 490c98aeb88a2d93b014b59f4c1a07573a13c0d1 Author: ModelHub XC Date: Thu Jun 4 01:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4cde69e --- /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 +LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaAligned-DeepSeekR1-Distill-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.IQ4_XS.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.IQ4_XS.gguf new file mode 100644 index 0000000..c7753f1 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6fa391dd7bd1c882a9d7bbee5eae0d8d729c50f35b234a70b78a8aa32e2997 +size 4484366048 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q2_K.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q2_K.gguf new file mode 100644 index 0000000..3ffd660 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189c88914e25ed868bb6c334af190645a6b28f75ef5fcc9eaeecb541dd0c5b12 +size 3179134688 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_L.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_L.gguf new file mode 100644 index 0000000..ed34ff9 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d20d4ed43a374c7d8066e97eac75d1fedb6abf8cfbefc1efc5c5eb774a9e878 +size 4321959648 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_M.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_M.gguf new file mode 100644 index 0000000..5d9c368 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f6d2446ba7896d7c1a0e1d5e2f9ed3a8c4cb95be76734134add6e74a44d3f5 +size 4018921184 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_S.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_S.gguf new file mode 100644 index 0000000..01da4a0 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71cc688f7e10c5f61513f2b36de457476321a22ec44993261489cf039937dba0 +size 3664502496 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_M.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_M.gguf new file mode 100644 index 0000000..fb48c83 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a838a3f76fb4ab8b2ef6a9c09187a8682788135b365e84b5dc7f7f37753e215e +size 4920737504 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_S.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_S.gguf new file mode 100644 index 0000000..a6186e0 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9208f966a7c4d4d4c624172143b72c3eaa344872c055483f28a7fd979dd994a +size 4692672224 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_M.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_M.gguf new file mode 100644 index 0000000..93fe591 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3c400abb213435b0d81210009f0a982e5d33497facd9e3a180e9f544b6457f +size 5732990688 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_S.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_S.gguf new file mode 100644 index 0000000..75940f2 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09284fafe6667a5b0765c8298d0c88c842664b888dd7353210799bbc0fa6c244 +size 5599297248 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q6_K.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q6_K.gguf new file mode 100644 index 0000000..44b0797 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd290427b30a5b13adf0e2b581c4600325e15271ad8f9e4aa188489eb6039a09 +size 6596009696 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.Q8_0.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.Q8_0.gguf new file mode 100644 index 0000000..8315d2f --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20e58410819607ee582345b64e78aa3e4c394be52ffa8d979063b42d1bf26ab +size 8540774112 diff --git a/LlamaAligned-DeepSeekR1-Distill-8b.f16.gguf b/LlamaAligned-DeepSeekR1-Distill-8b.f16.gguf new file mode 100644 index 0000000..c043896 --- /dev/null +++ b/LlamaAligned-DeepSeekR1-Distill-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823cedb4889a02e1c7220f38e9bc4ee0804b3dbd3a3ae37ff6324c3b6c85a3e4 +size 16068894432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b117d85 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: BlueBeck/LlamaAligned-DeepSeekR1-Distill-8b +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BlueBeck/LlamaAligned-DeepSeekR1-Distill-8b + + +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/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaAligned-DeepSeekR1-Distill-8b-GGUF/resolve/main/LlamaAligned-DeepSeekR1-Distill-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. + +