commit c2282713d23289a9828e7b6cd11ec7c5ea24d397 Author: ModelHub XC Date: Wed Jun 3 02:22:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4bcbc7d --- /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-2M-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-2M-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.IQ4_XS.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..d8ef6d8 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c968fd13126401fbe43ae0d5f2bc594e9e3f18d5d7ec741b471b665fdc3c12 +size 4488637184 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q2_K.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q2_K.gguf new file mode 100644 index 0000000..59c08d9 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b8dd9ac50a1b2a91f47615d9987a7b345e0525a30487b0b263b03012cf552d +size 3182766848 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_L.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..0cc2b9d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6ca4c78ae7200b15d393d43ae8dd6c99b580047f81751d195475caf9f5b68f +size 4325911296 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_M.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..1eba5ea --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8671565bcdf72689ce768f0ab16fb5f96a78ddbb76fc42b7b377932f959a9d87 +size 4022872832 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_S.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..4ef6591 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c59dd56adb68e391c1b8f550bc303644618c76bb90f371eb222b354aa7b9d1 +size 3668454144 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_M.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f93561c --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94a28370ceb3ab90bb166cd1dd6bc8eeffa6450339463f142718db2307c51c9 +size 4925106944 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_S.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..02023d9 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1745346ad87927d17ea2605043df3ca96a7408d64d7e37a7718e8703443ca7c +size 4697041664 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_M.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bb24cad --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7052af36293bd707c2418b0c771cb1de0499d8b9434d0c89165aeb8de76e4b +size 5737753344 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_S.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..cbdccd5 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8333b99ca62bca889d0785174f40c3dc3175ba8b56396afd41df74779ef666 +size 5604059904 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q6_K.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q6_K.gguf new file mode 100644 index 0000000..e787713 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c420235eb8187df34b506ebb82b186bf58067a499679b02e30ec8e1706a93552 +size 6601190144 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.Q8_0.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.Q8_0.gguf new file mode 100644 index 0000000..fdb2718 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaac56c9947af307b11f0358e71a792b24a8ab4ff3b66f1b9510f12b67418884 +size 8547478272 diff --git a/Llama-3.1-8B-UltraLong-2M-Instruct.f16.gguf b/Llama-3.1-8B-UltraLong-2M-Instruct.f16.gguf new file mode 100644 index 0000000..91582b0 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-2M-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b683804bb20090d56e1bd66f498dd49ccfb5dd879fc1b5fecf868577d5e826de +size 16081496832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..440b1b6 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-2M-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-2M-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-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-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF/resolve/main/Llama-3.1-8B-UltraLong-2M-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. + +