From 68cb64d54025644bd4544852b2411f15b09e0dfd Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 18 Jun 2026 04:56:17 +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/llama-3.1-8b-bias-reduced-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++++ README.md | 85 +++++++++++++++++++++++ llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ3_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf | 3 + llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q2_K.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q4_0.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q4_1.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf | 3 + llama-3.1-8b-bias-reduced.i1-Q6_K.gguf | 3 + llama-3.1-8b-bias-reduced.imatrix.gguf | 3 + 27 files changed, 220 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ3_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q2_K.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q4_0.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q4_1.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf create mode 100644 llama-3.1-8b-bias-reduced.i1-Q6_K.gguf create mode 100644 llama-3.1-8b-bias-reduced.imatrix.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88a4f7a --- /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 +llama-3.1-8b-bias-reduced.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-bias-reduced.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..3625eaf --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: hirundo-io/llama-3.1-8b-bias-reduced +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/hirundo-io/llama-3.1-8b-bias-reduced + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8b-bias-reduced-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-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/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-bias-reduced-i1-GGUF/resolve/main/llama-3.1-8b-bias-reduced.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/llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf b/llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf new file mode 100644 index 0000000..d1d5549 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8735a7b6582d1b79ab738fe053c36b93173c8b6aa1985942d024b241b776a1 +size 2161977088 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf b/llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf new file mode 100644 index 0000000..360c765 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5688e02d6b61bd3063a9549ef4fc18355cc53d6734de033cd54eaded32742ae +size 2019632896 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf b/llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf new file mode 100644 index 0000000..e6d995d --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f10f58c0839402faf0435161ef8bbe36ffa9a430f3d5273b9923932277302f +size 2948286208 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf b/llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf new file mode 100644 index 0000000..faf7282 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07654602d0fdfcc902ccc00fb4c020b970b498b93abdfd2671fa8b6678c7076 +size 2758493952 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf b/llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf new file mode 100644 index 0000000..87f9aa4 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ace203ed25d0b3742dff0ae921f082887afbb51680fcf9521b22308ded73d94 +size 2605786880 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf b/llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d8858d9 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df33129f1a49d1e0622df838410c885b2352a2998adc90f2181c81d7d48f5ca9 +size 2399217408 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf b/llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf new file mode 100644 index 0000000..924c100 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61dbc63a2e1c527aad55e49eba87e78ef797f0b384c5d1c7be0e61345751489 +size 3784828672 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ3_S.gguf b/llama-3.1-8b-bias-reduced.i1-IQ3_S.gguf new file mode 100644 index 0000000..446a257 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be946390c4a8e6c27270e9ecc165d7f85559570585852068e5d6bce400b53c2d +size 3682330368 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf b/llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e75c665 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37483bcbf91837328504c8bb3cb761176ace4be6f95c09044c8b4fed3702531d +size 3518752512 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf b/llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bb102dc --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ee5505bf82da3faba38c3f6404bac28c60fca3be4f6ce80e4cdf5a39c7c29e +size 3274917632 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf b/llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf new file mode 100644 index 0000000..92d2352 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc1a8218550934dd00bfde07871d3a2abdf376bbc4ca0c3a9780b419c1ff3c3a +size 4677994240 diff --git a/llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf b/llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf new file mode 100644 index 0000000..516b70a --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d03f2c485041f5e4219526f94ea7303f904c87698a15001b1f9a3526c7bf800 +size 4447667968 diff --git a/llama-3.1-8b-bias-reduced.i1-Q2_K.gguf b/llama-3.1-8b-bias-reduced.i1-Q2_K.gguf new file mode 100644 index 0000000..a7e68db --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc76fccdd38587475aaffe93587d0cbdaf33c8f8d36ba8de09128575e2134d0 +size 3179136768 diff --git a/llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf b/llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf new file mode 100644 index 0000000..05fef8c --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8bc2c7935b13c6d82876fb6d52c22a545e012c78692de09c9df480eed3fea66 +size 2988820224 diff --git a/llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf b/llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ef8ff0a --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e0114efd01d38f191e490a932ca2c1d423b96d239e7b2435a4e60f13d30b70 +size 4321961728 diff --git a/llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf b/llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf new file mode 100644 index 0000000..cc6895b --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a3a1690a19f3d598f0c195bea0fe5b76a5b04d742aaf5a5749af712feb94be +size 4018923264 diff --git a/llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf b/llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6351278 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46ba5633f2390e89b7df7d531f3692ff6e73221e2972f42d48d3d8eaecead2b +size 3664504576 diff --git a/llama-3.1-8b-bias-reduced.i1-Q4_0.gguf b/llama-3.1-8b-bias-reduced.i1-Q4_0.gguf new file mode 100644 index 0000000..d8b1a8d --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea1282295b2090221c99b4ee8ce2a41fe5c1d9fe6b85a2675ded21c5dbcf18e +size 4675897088 diff --git a/llama-3.1-8b-bias-reduced.i1-Q4_1.gguf b/llama-3.1-8b-bias-reduced.i1-Q4_1.gguf new file mode 100644 index 0000000..5df7095 --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1699834a8fc3ddbdb5374001afa889dec36fe100965124ead75213f34ca9f2a +size 5130258176 diff --git a/llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf b/llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf new file mode 100644 index 0000000..26be37c --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0cfdccb519ff7e74798aef08651b6d5df7394ea911dc2ccf875a911a8eb383d +size 4920739584 diff --git a/llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf b/llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9c92edf --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0808d3c5e3f0a7c1bb49ca52ed8e94c572e594cc09e951bba0418d94c3c98706 +size 4692674304 diff --git a/llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf b/llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b324d7c --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1280a0f60206077c4dfe942123feea9253935d0228811ff3613054b06467013 +size 5732992768 diff --git a/llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf b/llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf new file mode 100644 index 0000000..999494d --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ddcb0593ec8eb7fd39c48ebe2d47f0cf9623a09e6814e0b4227494665672173 +size 5599299328 diff --git a/llama-3.1-8b-bias-reduced.i1-Q6_K.gguf b/llama-3.1-8b-bias-reduced.i1-Q6_K.gguf new file mode 100644 index 0000000..69fffef --- /dev/null +++ b/llama-3.1-8b-bias-reduced.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78b6581e58d165421efda91cc7a3c7d3663ba8e05086e635529bdde7b484843f +size 6596011776 diff --git a/llama-3.1-8b-bias-reduced.imatrix.gguf b/llama-3.1-8b-bias-reduced.imatrix.gguf new file mode 100644 index 0000000..b1d86aa --- /dev/null +++ b/llama-3.1-8b-bias-reduced.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d038807f85f365135bbaba9cfacede4dd9e4c46d7df8eb9c405c686577a7cb +size 5015200