commit ef6f8902d917738e2a169c772e06b850461a17d3 Author: ModelHub XC Date: Sun Jun 14 13:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gary-nemotron-8b-v2-merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..de85ab0 --- /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 +gary-nemotron-8b-v2-merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.f16.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gary-nemotron-8b-v2-merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8fa4e80 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: SMOK33Y3/gary-nemotron-8b-v2-merged +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/SMOK33Y3/gary-nemotron-8b-v2-merged + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gary-nemotron-8b-v2-merged-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/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gary-nemotron-8b-v2-merged-GGUF/resolve/main/gary-nemotron-8b-v2-merged.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. + + diff --git a/gary-nemotron-8b-v2-merged.IQ4_XS.gguf b/gary-nemotron-8b-v2-merged.IQ4_XS.gguf new file mode 100644 index 0000000..6156e66 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840b473f36804fdb9ef92a5e14bbc0e02fbed575ce260473d8536a10232323c6 +size 4484365856 diff --git a/gary-nemotron-8b-v2-merged.Q2_K.gguf b/gary-nemotron-8b-v2-merged.Q2_K.gguf new file mode 100644 index 0000000..0b64f69 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be89ccae847dcec7bd83548bbd0936cb776fbad1c8ea1f9582c16f94f31422d +size 3179134496 diff --git a/gary-nemotron-8b-v2-merged.Q3_K_L.gguf b/gary-nemotron-8b-v2-merged.Q3_K_L.gguf new file mode 100644 index 0000000..69d312c --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2230d1325bc84ca41f2042f3e564e5b3bfc8451f7dd5b1ee0ab20c7bef70c1d3 +size 4321959456 diff --git a/gary-nemotron-8b-v2-merged.Q3_K_M.gguf b/gary-nemotron-8b-v2-merged.Q3_K_M.gguf new file mode 100644 index 0000000..452a9ec --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2e48fa72c00ad58add6aea688bd1404781a06471b451306bf6307be741f6378 +size 4018920992 diff --git a/gary-nemotron-8b-v2-merged.Q3_K_S.gguf b/gary-nemotron-8b-v2-merged.Q3_K_S.gguf new file mode 100644 index 0000000..ca27942 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73daf8367a64ae2aa1fd2c0ddd18007a7a536c5753964b9ff236964dbed49835 +size 3664502304 diff --git a/gary-nemotron-8b-v2-merged.Q4_K_M.gguf b/gary-nemotron-8b-v2-merged.Q4_K_M.gguf new file mode 100644 index 0000000..3188d7f --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7bbdc6f69660f76212dfbe3eb810912d6a37225aaed84c9e7c47a0e1df665ba +size 4920737312 diff --git a/gary-nemotron-8b-v2-merged.Q4_K_S.gguf b/gary-nemotron-8b-v2-merged.Q4_K_S.gguf new file mode 100644 index 0000000..e773056 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7644a082f6ef25b0d704fb7cdfd0d0b82d6e12eba5fc47a91060c53513a254 +size 4692672032 diff --git a/gary-nemotron-8b-v2-merged.Q5_K_M.gguf b/gary-nemotron-8b-v2-merged.Q5_K_M.gguf new file mode 100644 index 0000000..8bd14d4 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da3c469a0fab96742ce1dfd6fa451c9f11b6a23720affc73360b739e607bcd8 +size 5732990496 diff --git a/gary-nemotron-8b-v2-merged.Q5_K_S.gguf b/gary-nemotron-8b-v2-merged.Q5_K_S.gguf new file mode 100644 index 0000000..df2f748 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32abdc62ef4aa14cad51b82ae386ae87082feae163f1dfedcbeb076a137f07e8 +size 5599297056 diff --git a/gary-nemotron-8b-v2-merged.Q6_K.gguf b/gary-nemotron-8b-v2-merged.Q6_K.gguf new file mode 100644 index 0000000..1c265ee --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c528d7b847c4db1d8a2c711e3fa022d1cf2958e3735ef07823675fbea00cac6b +size 6596009504 diff --git a/gary-nemotron-8b-v2-merged.Q8_0.gguf b/gary-nemotron-8b-v2-merged.Q8_0.gguf new file mode 100644 index 0000000..7dca75d --- /dev/null +++ b/gary-nemotron-8b-v2-merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb40858a4193de6d016216edc912e06f1934072b9a988797c6318e81f11631aa +size 8540773920 diff --git a/gary-nemotron-8b-v2-merged.f16.gguf b/gary-nemotron-8b-v2-merged.f16.gguf new file mode 100644 index 0000000..64c90e8 --- /dev/null +++ b/gary-nemotron-8b-v2-merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1d7b7a5b8e8008ffd341735e4ed5f7784a157d7428e542edb468a8a071660e +size 16068894240