commit 83a5544c49f61b711b345d93723c203eed5d2a70 Author: ModelHub XC Date: Sat May 9 07:45:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..97a53c9 --- /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 +Llama3.1-8B-Nemotron-Python-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-Python-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Nemotron-Python-v2.IQ4_XS.gguf b/Llama3.1-8B-Nemotron-Python-v2.IQ4_XS.gguf new file mode 100644 index 0000000..a1c7689 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9e0f52b0a64f1585839191c1a1777ac3333fa63a29e9281682d197ccedcd55 +size 2553243232 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q2_K.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q2_K.gguf new file mode 100644 index 0000000..7181823 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc349f75ec8986320db0c7010856e6eab2048eb16c6d321ceafc7ec3091ab418 +size 1839740512 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q3_K_L.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q3_K_L.gguf new file mode 100644 index 0000000..1ee00e1 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb53ad78eb58dc16520e7c1afe62daecec1b29aed36605782d7483179c83a7d4 +size 2464861792 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q3_K_M.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q3_K_M.gguf new file mode 100644 index 0000000..3e86f5c --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a3d47b647c034b777069ecd43e93e05f267338d934bfbe1971d590e38f0b30 +size 2296565344 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q3_K_S.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q3_K_S.gguf new file mode 100644 index 0000000..2828dd9 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e04f9cfe86dd7ae8fa4257a4c3d152422046b0918aa76c0db9c5f12f2ea6be0 +size 2101530208 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q4_K_M.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q4_K_M.gguf new file mode 100644 index 0000000..229cc3c --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8a932035770fbbbb7d502b0d2b77f697bb627b400c52606663263510773fb5 +size 2778285664 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q4_K_S.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q4_K_S.gguf new file mode 100644 index 0000000..649795b --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52fe16f4be8441c06be994c04b43e8111858b834ba672b839f9a21175f99ac55 +size 2664253024 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q5_K_M.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q5_K_M.gguf new file mode 100644 index 0000000..2424f06 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad4676ed0a0ab31bc4b10afb5cc543a901ecd9d8e7fdc87c48e669e2fcc8129 +size 3230189152 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q5_K_S.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q5_K_S.gguf new file mode 100644 index 0000000..1a73f5b --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa07c7a55d5bee3e1895feb91673affd226e025b146ec094cc11f71e10b0df5c +size 3163342432 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q6_K.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q6_K.gguf new file mode 100644 index 0000000..737f5b1 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35c6aed03ab16ccec28e7d50377ad894992cbf3696d3b2d03a74b560640091c +size 3710336608 diff --git a/Llama3.1-8B-Nemotron-Python-v2.Q8_0.gguf b/Llama3.1-8B-Nemotron-Python-v2.Q8_0.gguf new file mode 100644 index 0000000..2c7d447 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db0a6ed0529228407dd95f642bf124813fd7da26a0bbd56cf600bda6274c5961 +size 4803219040 diff --git a/Llama3.1-8B-Nemotron-Python-v2.f16.gguf b/Llama3.1-8B-Nemotron-Python-v2.f16.gguf new file mode 100644 index 0000000..511de92 --- /dev/null +++ b/Llama3.1-8B-Nemotron-Python-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe466d2c5923ee06c40a6ae0a123da5327cf12e58f52559740c7e5b007d474a +size 9033731680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7dd042 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Montecarlo2024/Llama3.1-8B-Nemotron-Python-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Montecarlo2024/Llama3.1-8B-Nemotron-Python-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-Nemotron-Python-v2-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.IQ4_XS.gguf) | IQ4_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q5_K_S.gguf) | Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q6_K.gguf) | Q6_K | 3.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-Python-v2-GGUF/resolve/main/Llama3.1-8B-Nemotron-Python-v2.f16.gguf) | f16 | 9.1 | 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. + +