From 87f7d412bd10e3ffbbfcafe0c0a9b0c577fce647 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 11 Jun 2026 14:55:16 +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-UltraLong-4M-Instruct-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++ ...a-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf | 3 + Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf | 3 + ...a-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf | 3 + Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf | 3 + Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf | 3 + Llama-3.1-8B-UltraLong-4M-Instruct.f16.gguf | 3 + README.md | 64 +++++++++++++++++++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf create mode 100644 Llama-3.1-8B-UltraLong-4M-Instruct.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6d61e0 --- /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 +Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..de4f4e1 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4eecde7920d768888a892bc8c87d96409045a39a102daa0eb1b535333a790b +size 4488637184 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf new file mode 100644 index 0000000..8e8c92a --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f286eff0347901a3b9814369aceb650f2b9a72484b9730c26cad56a3a448fb23 +size 3182766848 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..f6321fa --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701bc8b1a307b2e24897730d67d9e606959e0e388ce9e4f437ad57783b7cfd1a +size 4325911296 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..c2f3f3d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d278a3d31d9720456d3957df0ff0ef9d0afc8158dee896771e55e9e5366b8ca6 +size 4022872832 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..77ee077 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd8e44c67fb21085d212f17ecdcec50e719cb9dda06677af2c3e3d32f74af42 +size 3668454144 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c48baa2 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8179a50ec221bb1ca2abaa2c2e447016aad72e1e8cc1f217777791d81a3791 +size 4925106944 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..45de395 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d3acf19bae447637590a4ae9dd9322f2d0459b69ef80e4b6565993d70035bd +size 4697041664 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..77cdc90 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c74d315653fc1ecfe245e12c421b096df2d2439284c5299ae13cf497826ae66 +size 5737753344 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..21e677c --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd1e97d1f12459b61c454f9fd7acda5f093334bd10a5287129861ee052b18fb +size 5604059904 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf new file mode 100644 index 0000000..3dae1a5 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea88758a6de66a751a924e0f7626431b36e52250600849e506d1d12514e01d87 +size 6601190144 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf new file mode 100644 index 0000000..2913573 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187f1d6fef1e6bc781a1c9a14c19d80cce0a22e0e8ff20ce614afda809cc468a +size 8547478272 diff --git a/Llama-3.1-8B-UltraLong-4M-Instruct.f16.gguf b/Llama-3.1-8B-UltraLong-4M-Instruct.f16.gguf new file mode 100644 index 0000000..ddb47a3 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-4M-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ca6821df60c3b2f3752a2097d2e4310e9ed809fd33553fd1a8188d9a7a6e19 +size 16081496832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0fff822 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-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/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-4M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-4M-Instruct.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. + +