commit ea3aae0b6bd041aec3c0c15007620037edc277ed Author: ModelHub XC Date: Sun Jun 14 00:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f8aa1d3 --- /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-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.IQ4_XS.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.IQ4_XS.gguf new file mode 100644 index 0000000..c8011c7 --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1383a78b7a667ee6564dab73647fa44892266c9af6aedc2e28f4ef2499065e91 +size 4488637728 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q2_K.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q2_K.gguf new file mode 100644 index 0000000..7168d5b --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c339ae8d70be192fbe237de1c024fe448448e532663bf006be40e57bb1c47ff +size 3182767392 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_L.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_L.gguf new file mode 100644 index 0000000..5af3c19 --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ef00912a59b365c405e25fe28f1b8bc9409d9b7edc618bd4e15a53f1628a67 +size 4325911840 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_M.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_M.gguf new file mode 100644 index 0000000..937688b --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373a8dff480b3dff3b0fc68e506cb1503a7913dbe0279786027f3a3966280e99 +size 4022873376 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_S.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_S.gguf new file mode 100644 index 0000000..6c2d3d0 --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a65e09982edc1ec31735c54f81c37ce27df9dc95b855cb9757a3f939f11393c +size 3668454688 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_M.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_M.gguf new file mode 100644 index 0000000..178f808 --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a3f9bd7517991295fa689c5a54ee697adc96545196f1190f023bca697f9574 +size 4925107488 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_S.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_S.gguf new file mode 100644 index 0000000..f5a07c6 --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9b098154f1c74e357f91faa96fb72202318888fa9f9b57f8b0d0361f8a4fb2 +size 4697042208 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_M.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_M.gguf new file mode 100644 index 0000000..005a7ed --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b797b68b75b6225183b019ab08ebda5827ea55b818ca84bae5a08a49befb7499 +size 5737753888 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_S.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_S.gguf new file mode 100644 index 0000000..a954b1f --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453877ef335ba1c9c9a42fef047205b14b4f44f8c5f58d5a50f4d9b0244df952 +size 5604060448 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q6_K.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q6_K.gguf new file mode 100644 index 0000000..ae6539b --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83222e3da2def3b5b72b38eae2a56e3b39fc0e89add34bd0c40411342fb710f +size 6601190688 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q8_0.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q8_0.gguf new file mode 100644 index 0000000..32ebefb --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e78e4cab50f00cbacc1dd3e5fbcbbe273ecf04b221f607a936e8242f8b9838 +size 8547478816 diff --git a/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.f16.gguf b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.f16.gguf new file mode 100644 index 0000000..342c2f2 --- /dev/null +++ b/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86800c58ee59bcddee0a1519bdf822a83d4d3ab7789caf37f40f7435ca1f97b7 +size 16081497376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c73cc2 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: MuXodious/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +- uncensored +- decensored +- abliterated +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MuXodious/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-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-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy-GGUF/resolve/main/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy.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. + +