From 288ea7540d65b9e0741290730157e8f079d0dee1 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 31 Jul 2026 14:50:17 +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-UltraLong-1M-Instruct-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++ ...a-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf | 3 + Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q4_K_S.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf | 3 + ...a-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf | 3 + Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf | 3 + Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf | 3 + Llama-3.1-8B-UltraLong-1M-Instruct.f16.gguf | 3 + README.md | 64 +++++++++++++++++++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d769039 --- /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-1M-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9df7270 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec0495fb20965f7ceb950322ab365dd377cc4a6d3187c7a053c6ad8a6e4d390 +size 4488637184 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf new file mode 100644 index 0000000..4334a0b --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e443ee61d51b9d47140242502cb0745539619cf838f09a972c93f4260329c85 +size 3182766848 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..4e56385 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b466a82da322412a39678fed3f5da39311913786567a3c96abfd52d0c80768f +size 4325911296 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..98f687a --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12abf155aee220b87aacfb7eb2a5a82391b9d85f11dd21c6054afd1f64dc05af +size 4022872832 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..51bba0d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c3cd65b5deb7cc186d1fb632f29cf3753d9ecca1e5c62eeff83b95ead4a85f +size 3668454144 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..49d8e44 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837ef4ccd861719261fbfd417deae68a24d5649f07b3cde1c12779d103f3e1a5 +size 4925106944 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..3f2cddd --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e2ac22f4c2a5cd68d3871bf8c272016dd4f4b5f4abfd2792305a832cd5cc9c +size 4697041664 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..280d33d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ba4f93ec86d8def5a72b4593a1b9565222a70299ebb56a0a0043fb8514dd0c +size 5737753344 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8b8b11a --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e655b374e59e17d324d99cf1ba3350a8b2bfc215df8709a1151e72e5cf2c48 +size 5604059904 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf new file mode 100644 index 0000000..106f30f --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:452cbaca28ed3bcffd55f6dc52ea525ca4eb8cf5f3c6d2331aef493bdeb4f975 +size 6601190144 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf new file mode 100644 index 0000000..c0461f3 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e4c1f6fd65d981ae06a8b977947226809a265e8d0bbcc0f7ba1f311129fa1d +size 8547478272 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.f16.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.f16.gguf new file mode 100644 index 0000000..e3f40c1 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5ba38da8005a686b318815732a4ca4128bc4b56293e1ec741dafb513fca090f +size 16081496832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc88430 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-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-1M-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-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-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-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. + +