commit 3e7d32eb997498c872e362cd43fdddd4573ac62d Author: ModelHub XC Date: Sat Jun 13 05:58:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2fff0be --- /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 +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.IQ4_XS.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..5b06eef --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887e419458fdc31f50f79818fb90df195d101c040a9e9a330155893c28742c60 +size 4484365856 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q2_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..76b3ef0 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09bb0c82d72bbb663f42a24d452f8a1abac316d483aa4f93ec2397a52f1f978e +size 3179134496 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_L.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..8acd97c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f907dd11a5d48ce53c5625572a02d36a29a56882d15ac43eb99721a92cb7a415 +size 4321959456 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..7f828f8 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2673304d378db5dc135d68a62762f718620579b3bfa854ef7a5e9426bdebc8a0 +size 4018920992 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..a93fc1a --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e161aacca6788ebd48642a03307216497de3c478448821ef7499202c59caa2 +size 3664502304 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..1c2b81d --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66be9e32013a42cb4f7d6e00e99c45b9aa013c08ebfc0adeb7798af2ce401348 +size 4920737312 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..69a82b1 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7bc38e41011c7923982ae565d38df6d7649d67e50566fdaa58f6280d436ab2 +size 4692672032 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..375c061 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed97428e633d22035fa0e30d75d7a5111c5c9f17d4a79173f3bd84a00d890684 +size 5732990496 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..96f6018 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176f6ac77b476b6e4e1623a0b1078bdfdc461443dc2023f54a406b44cade9a83 +size 5599297056 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q6_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..536d1f3 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9575caf68c9febb486d410b7326388471f37a6eef7a3897f2a403ba5c2a0d3 +size 6596009504 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q8_0.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..a058bee --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5803805583cfc981e18c2063ace94e3e5716e0e510f47e1ed838aa7b6a9cd9a +size 8540773920 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.f16.gguf b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.f16.gguf new file mode 100644 index 0000000..128af7d --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfa6a92feb64ed362b99c8ac59767976be3325d1eb5c6792000e801dd69c3b7 +size 16068894240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f9cc36d --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: DimensionSTP/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning +language: +- ko +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- korean +- reasoning +- instruction-tuning +- fine-tuning +- llama +- desspseek +- distillation +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DimensionSTP/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF).*** + +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/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ko-Reasoning.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. + +