commit 802337a345349be4cbfafbe626ef8532941971e3 Author: ModelHub XC Date: Fri Jun 12 00:50:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed47e75 --- /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-DRAFT-0.6B-v3.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-DRAFT-0.6B-v3.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.IQ4_XS.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.IQ4_XS.gguf new file mode 100644 index 0000000..691e655 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e18fe993597482f907de9f7546f8c81c4418273805dd44107427475bcd55dc +size 394336896 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q2_K.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q2_K.gguf new file mode 100644 index 0000000..cd8e61b --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214f7d842b5e8b062dbb4097f9951d68259b346b84e3258cdb4214483ec49398 +size 381499008 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_L.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_L.gguf new file mode 100644 index 0000000..0e17b7c --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f23f52965a2eb452fe551a896f0bdff63aeda2276f5eae60e6be761b88ff1a4 +size 412249728 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_M.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_M.gguf new file mode 100644 index 0000000..b0792a8 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d72650d1463e4d9163a0dd237de8881ec0f3aa1434a7a19c51e75daed8d18a +size 398358144 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_S.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_S.gguf new file mode 100644 index 0000000..848e876 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f423d41758006a71811fe8ad2b1e652b4516ce2cf8aeddf54c017ec50098d9a8 +size 381154944 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_M.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_M.gguf new file mode 100644 index 0000000..1f55f79 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed71386119b3fe79c56b2dc755074a2541d28104bcfe96bd56562ac2f95b9b0d +size 455178880 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_S.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_S.gguf new file mode 100644 index 0000000..c92db63 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a50121af665cf7f8a803435ab493f8766e8e752a0705c5c03c8bbf9e581cb33 +size 442842752 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_M.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_M.gguf new file mode 100644 index 0000000..e5fec6a --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcd093b47cecd1177847da1bce56fdee444ddb9c6292b0c2d53d5436f064cc6 +size 484696704 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_S.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_S.gguf new file mode 100644 index 0000000..fad4df3 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3fa2cd63052ec3c1319b4cd4c924bc0b4010752c40778b0efa2c916dc4b903 +size 477320832 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q6_K.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q6_K.gguf new file mode 100644 index 0000000..e3bd384 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0391718fe495eca8020441f6e56cddefc7c85f67aa301133d678244f45bf6b28 +size 606545536 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.Q8_0.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q8_0.gguf new file mode 100644 index 0000000..559f0b6 --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e973bb0a1dec5d676e8571fcbca42b3d3213c710418d6d0aae6238c2a53a75a +size 631877248 diff --git a/DeepSeek-R1-DRAFT-0.6B-v3.0.f16.gguf b/DeepSeek-R1-DRAFT-0.6B-v3.0.f16.gguf new file mode 100644 index 0000000..bd391cb --- /dev/null +++ b/DeepSeek-R1-DRAFT-0.6B-v3.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c3e6f9bb77b096cb2a8b42b8f18972d5f8c885e838ed3a4805d2ee4520a05a +size 1184530048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0584393 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: jukofyork/DeepSeek-R1-DRAFT-0.6B-v3.0 +datasets: +- agentlans/common-crawl-sample +- bigcode/the-stack-smol-xl +- rombodawg/Everything_Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- draft +- speculative-decoding +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jukofyork/DeepSeek-R1-DRAFT-0.6B-v3.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-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/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-R1-DRAFT-0.6B-v3.0.f16.gguf) | f16 | 1.3 | 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. + +