commit 751ab7caf2cc8a6558328619a3ddb9a41270139f Author: ModelHub XC Date: Tue Jun 2 21:06:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0477a3f --- /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 +Nemotron-Nano-9B-v2-heretic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.f16.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Nano-9B-v2-heretic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nemotron-Nano-9B-v2-heretic.IQ4_XS.gguf b/Nemotron-Nano-9B-v2-heretic.IQ4_XS.gguf new file mode 100644 index 0000000..e30ab01 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2de5b6b5067df3c72a65868e48a6767ef17f908b5cca2bec36bb8b5be6942b +size 5359306592 diff --git a/Nemotron-Nano-9B-v2-heretic.Q2_K.gguf b/Nemotron-Nano-9B-v2-heretic.Q2_K.gguf new file mode 100644 index 0000000..ccc625b --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc79be8645b9d8793c6cea8bcb22819780af19b7a701464ebc283a0a80842d0 +size 5006192992 diff --git a/Nemotron-Nano-9B-v2-heretic.Q3_K_L.gguf b/Nemotron-Nano-9B-v2-heretic.Q3_K_L.gguf new file mode 100644 index 0000000..0536db9 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e624a883d74736cba3b8c2e2e36c360fcb9c105080fe457a48d8977ff5bd62e0 +size 5488366432 diff --git a/Nemotron-Nano-9B-v2-heretic.Q3_K_M.gguf b/Nemotron-Nano-9B-v2-heretic.Q3_K_M.gguf new file mode 100644 index 0000000..6157f63 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5662cd3df2438cf529fbea4e5b30f7e670abed385583364deb5da3e594a46c12 +size 5379735392 diff --git a/Nemotron-Nano-9B-v2-heretic.Q3_K_S.gguf b/Nemotron-Nano-9B-v2-heretic.Q3_K_S.gguf new file mode 100644 index 0000000..eeed045 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1e433ff030e22763c4d6900ff02f7ff1c83e2db6a559aee7a14fd7b12529d9 +size 5131991392 diff --git a/Nemotron-Nano-9B-v2-heretic.Q4_K_M.gguf b/Nemotron-Nano-9B-v2-heretic.Q4_K_M.gguf new file mode 100644 index 0000000..9cb062b --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0a25bfa91cf0a6d989635bf148fe41760faec9c0fa18d4fb53a9b463d9a081 +size 6525629792 diff --git a/Nemotron-Nano-9B-v2-heretic.Q4_K_S.gguf b/Nemotron-Nano-9B-v2-heretic.Q4_K_S.gguf new file mode 100644 index 0000000..1ac8668 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd66d13e31c59573cfe03e6761faffd1e3311d8d58d4484d4396d61606a95d0 +size 6211617632 diff --git a/Nemotron-Nano-9B-v2-heretic.Q5_K_M.gguf b/Nemotron-Nano-9B-v2-heretic.Q5_K_M.gguf new file mode 100644 index 0000000..48041a2 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e35bff34df448599d46efa55ad14aab1d94b9371bb9b3f618bd61f19fe0ca2e +size 7069806432 diff --git a/Nemotron-Nano-9B-v2-heretic.Q5_K_S.gguf b/Nemotron-Nano-9B-v2-heretic.Q5_K_S.gguf new file mode 100644 index 0000000..aca0b11 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b172cee01a82442419970a2e82faf85da5d87f562abce6f6e01739d2479d1b +size 6781563232 diff --git a/Nemotron-Nano-9B-v2-heretic.Q6_K.gguf b/Nemotron-Nano-9B-v2-heretic.Q6_K.gguf new file mode 100644 index 0000000..07b0857 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72b62abe81aa8b99d7d78467e02d937aa2a1baacd60391a88ab18410a082904 +size 9135892832 diff --git a/Nemotron-Nano-9B-v2-heretic.Q8_0.gguf b/Nemotron-Nano-9B-v2-heretic.Q8_0.gguf new file mode 100644 index 0000000..612eb59 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c7109c71e8d643b5e74b133b7739e992aecebd7ffdef8a69e3dcd7372443ab +size 9458094432 diff --git a/Nemotron-Nano-9B-v2-heretic.f16.gguf b/Nemotron-Nano-9B-v2-heretic.f16.gguf new file mode 100644 index 0000000..b4e11f3 --- /dev/null +++ b/Nemotron-Nano-9B-v2-heretic.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0901001dcc43a3af81f610048d9336d916a095c5d3c6a0902b634187075045 +size 17788744032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f2c2731 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: cpagac/Nemotron-Nano-9B-v2-heretic +datasets: +- nvidia/Nemotron-Post-Training-Dataset-v1 +- nvidia/Nemotron-Post-Training-Dataset-v2 +- nvidia/Nemotron-Pretraining-Dataset-sample +- nvidia/Nemotron-CC-v2 +- nvidia/Nemotron-CC-Math-v1 +- nvidia/Nemotron-Pretraining-SFT-v1 +language: +- en +- es +- fr +- de +- it +- ja +library_name: transformers +license: other +license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ +license_name: nvidia-open-model-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nvidia +- pytorch +- heretic +- uncensored +- decensored +- abliterated +--- +## About + + + + + + + + + +static quants of https://huggingface.co/cpagac/Nemotron-Nano-9B-v2-heretic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nemotron-Nano-9B-v2-heretic-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-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/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q2_K.gguf) | Q2_K | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q3_K_S.gguf) | Q3_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.IQ4_XS.gguf) | IQ4_XS | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q3_K_L.gguf) | Q3_K_L | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q4_K_S.gguf) | Q4_K_S | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q5_K_S.gguf) | Q5_K_S | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q5_K_M.gguf) | Q5_K_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q6_K.gguf) | Q6_K | 9.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.Q8_0.gguf) | Q8_0 | 9.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Nano-9B-v2-heretic-GGUF/resolve/main/Nemotron-Nano-9B-v2-heretic.f16.gguf) | f16 | 17.9 | 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. + +