From 497a8b29bcec8dbb5e79f2ca8d8fa196b5b013ef Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 27 Sep 2026 06:09:18 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ README.md | 76 +++++++++++++++++++ ...thought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf | 3 + ...thought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf | 3 + ...thought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf | 3 + ...thought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf | 3 + ...ought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf | 3 + ...thought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf | 3 + ...thought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf | 3 + ...ought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf | 3 + deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf | 3 + deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf | 3 + deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf | 3 + ...hought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf | 3 + deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf | 3 + imatrix.dat | 3 + 27 files changed, 211 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf create mode 100644 deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c75124c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +deepthought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..425412c --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ruliad/deepthought-8b-llama-v0.01-alpha +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ruliad/deepthought-8b-llama-v0.01-alpha + + +static quants are available at https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-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/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/deepthought-8b-llama-v0.01-alpha-i1-GGUF/resolve/main/deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf new file mode 100644 index 0000000..81751bd --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf06a56603bd9c8a0bb5c8bd1375bde047b3035de8874764c6bd0b04e868fc07 +size 2161993984 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf new file mode 100644 index 0000000..7ccf8bd --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87056068358beed48b6651dbf8227cd44031800b18b6a3ea0f1f580a542b99c9 +size 2019649792 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf new file mode 100644 index 0000000..d500202 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b25e4f116c676bdfb90c673670b6cd5b1b13f59e2e0aec5c32b8c7cacceffa3 +size 2948304768 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf new file mode 100644 index 0000000..cc68084 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c94639231c6faffc5f995e7d243d1931a7923ad59dfc1458891398e88ad2b2 +size 2758512512 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0fc3f2d --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6777edcdf40325eeee117701b639683b6f447e4afb77e489c19ae8270a2a65 +size 2605803776 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4c728ef --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5542fc4d4ce8234838bf7dcbb29dd64f1a9ad26fd0d0886517ab5e2178af07ce +size 2399234304 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf new file mode 100644 index 0000000..e3c55ac --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3be624c095a210c7e7a258ca58b472ba12d9e184bc9f20bff022dc0fcdf7e2c +size 3784849408 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf new file mode 100644 index 0000000..d9dff74 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96392889fc9de1ec488b4fde96ebc57f7128566f6095c43c4f0e36efc3ac071f +size 3682351104 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2c05994 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0407781a4ba67e614974fe3c7b50b20770faded6570502c4802ad546e205767b +size 3518773248 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..65cf86f --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3deaba6f0559b59c32e26791d6dd28c94778267951886d9ef76dc1a02d295ab6 +size 3274936192 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf new file mode 100644 index 0000000..743383e --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3b0c187b021ce2397aaff9dafca796cab6960638eb280515ea1bf3a0915c4d +size 4678017152 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf b/deepthought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf new file mode 100644 index 0000000..94221c7 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb52c2b39900ff38649a1c6b59e6f908f9315a9b14f796717d32ddedb1bf976 +size 4447690368 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf new file mode 100644 index 0000000..fc42a43 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17229c04fc6d8233b64a5999b2c50dd145d9e4a3f61c5834953641ee2e8fcd29 +size 3179155840 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf new file mode 100644 index 0000000..783668f --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8daf964d14b1b9747f9857304e14993fcfd95d8fe0dda906da63544b98194ca9 +size 2988839296 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1c2cae4 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503b9814e84aa5d3724faf123a2da9123e7a27f8862463df84ecf0c73f87bbb0 +size 4321982464 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf new file mode 100644 index 0000000..35774e2 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61efad4e98bc6494147c723b8da75ea2461417c3429b35e35f5fac7c6657c787 +size 4018944000 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4a6ef10 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b907ebdff0ea8f07eb12da5cb0d90365f96f403f9151f5dd42c7256be225b108 +size 3664525312 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf new file mode 100644 index 0000000..ff5266f --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a2e9f9eda77bb1ef38f5b7a6ef89bb865c4b2517abc5e549f9e7bae00d20a3 +size 4675920000 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf new file mode 100644 index 0000000..57a3e48 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d147b7acf5407ce64fa1e2c11407116205dca51b66ef9d5f6f3567ea557794 +size 5130282112 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4982fbe --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a6e6d6578436566f825e0be5e26cf29ef34da1a5fc960d736d10fac180ec7c +size 4920762496 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1d32ead --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a58b5526de0c5da34d2e609b9ecb8e0f0cb0f2e092bfc4cfda67afdcd89b60 +size 4692697216 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f64c634 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6babd632b2f4b55335da325bd4ac1c42d090e9b1650503f53f2de5acee53e386 +size 5733017728 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d22c2c6 --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf76552a5b32e358c5988d6eb8a1709820bebfdcfbec91137cf82eed135e895d +size 5599324288 diff --git a/deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf b/deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf new file mode 100644 index 0000000..4c2232c --- /dev/null +++ b/deepthought-8b-llama-v0.01-alpha.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e1a0a6b60ba29eb604ad2e96c65f6a526b679c1070d18b01f64366b2a5d8a1 +size 6596038912 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..f7876eb --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466a36220c430ca1d395ec6ecf093dfa9c863d3bf9a10a1c48aab9a4a6d86772 +size 4988157