commit 983dc4bab0b9b6c11b74d140edaab3d6f8acfec6 Author: ModelHub XC Date: Thu Sep 10 02:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf085d6 --- /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-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Nemotron-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Nemotron-SFT.IQ4_XS.gguf b/Llama3.1-8B-Nemotron-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..199d771 --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b1e180ff19ba1c0475eb7d86adc1d9f866c0cc9696881f1e536ae4a9a72a8b +size 4484367904 diff --git a/Llama3.1-8B-Nemotron-SFT.Q2_K.gguf b/Llama3.1-8B-Nemotron-SFT.Q2_K.gguf new file mode 100644 index 0000000..d684ecb --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbca9516f1b5837b6a0256567010532459f31c330e6afca0b009ab6eb0ecd505 +size 3179136544 diff --git a/Llama3.1-8B-Nemotron-SFT.Q3_K_L.gguf b/Llama3.1-8B-Nemotron-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..01dba22 --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9398392722be9bc6c12fde17d68ae9b66e751a2bc8bf7197c6b4f1616a3c580 +size 4321961504 diff --git a/Llama3.1-8B-Nemotron-SFT.Q3_K_M.gguf b/Llama3.1-8B-Nemotron-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..58c48c7 --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f356b920143013b8e3958a5fa76ccf319893e2f413fa60881c3df3c6e1dd972 +size 4018923040 diff --git a/Llama3.1-8B-Nemotron-SFT.Q3_K_S.gguf b/Llama3.1-8B-Nemotron-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..0b3741c --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ea649e191d84f74127d584f527a19f25b5fa13cc55ec6e99ba2323aeb8ea3e +size 3664504352 diff --git a/Llama3.1-8B-Nemotron-SFT.Q4_K_M.gguf b/Llama3.1-8B-Nemotron-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..dcf20c8 --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89abc4de13fbcc989a339d0e426251f903c950525b2d35775f39a42cc9420009 +size 4920739360 diff --git a/Llama3.1-8B-Nemotron-SFT.Q4_K_S.gguf b/Llama3.1-8B-Nemotron-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..561123a --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed48faa09380acbb8e639563d5af50e837cc1d35e66f9e22adf582b7b11bfb9e +size 4692674080 diff --git a/Llama3.1-8B-Nemotron-SFT.Q5_K_M.gguf b/Llama3.1-8B-Nemotron-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..4d13dcd --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1381977002d8454685bdad02b79565839290670c75453b0ba5dfed00f2cfb5a5 +size 5732992544 diff --git a/Llama3.1-8B-Nemotron-SFT.Q5_K_S.gguf b/Llama3.1-8B-Nemotron-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..4d6a0aa --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ab4127bab2aadbb1589cf9e5be5906fc39a2b9ce0c89426d71d27c7c1c482b +size 5599299104 diff --git a/Llama3.1-8B-Nemotron-SFT.Q6_K.gguf b/Llama3.1-8B-Nemotron-SFT.Q6_K.gguf new file mode 100644 index 0000000..4c22673 --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2087e8b2f2aa913d286ee00aae36a9b34f6d1fb15294b037f39bd248340b2ecd +size 6596011552 diff --git a/Llama3.1-8B-Nemotron-SFT.Q8_0.gguf b/Llama3.1-8B-Nemotron-SFT.Q8_0.gguf new file mode 100644 index 0000000..00f872a --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544f6c9fad65c864800a16b08e7e77446c6fd251b6caed69d15d9c9e5b0edfdf +size 8540775968 diff --git a/Llama3.1-8B-Nemotron-SFT.f16.gguf b/Llama3.1-8B-Nemotron-SFT.f16.gguf new file mode 100644 index 0000000..7fdf60a --- /dev/null +++ b/Llama3.1-8B-Nemotron-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8219a0375f8a935db63ea010d4dbf7476f656929c2cbb521c64263b955d796a8 +size 16068896288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e2cbd3 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: TharunSivamani/Llama3.1-8B-Nemotron-SFT +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TharunSivamani/Llama3.1-8B-Nemotron-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-Nemotron-SFT-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-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Nemotron-SFT-GGUF/resolve/main/Llama3.1-8B-Nemotron-SFT.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. + +