commit 2285537ac740a26f988032efd54f656ff56a77fa Author: ModelHub XC Date: Sat May 9 03:45:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AceReason-Nemotron-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab12cf4 --- /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 +AceReason-Nemotron-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AceReason-Nemotron-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AceReason-Nemotron-7B.IQ4_XS.gguf b/AceReason-Nemotron-7B.IQ4_XS.gguf new file mode 100644 index 0000000..f2cf753 --- /dev/null +++ b/AceReason-Nemotron-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330306115a446c10f6b6d2939078fe918cabd4320d5f76d0a0262104c518ed52 +size 4250298496 diff --git a/AceReason-Nemotron-7B.Q2_K.gguf b/AceReason-Nemotron-7B.Q2_K.gguf new file mode 100644 index 0000000..fa120f4 --- /dev/null +++ b/AceReason-Nemotron-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a98402b42c3a94943d162a272bd4f02aab1229bbabe61d570ea6633419bf68e +size 3015940224 diff --git a/AceReason-Nemotron-7B.Q3_K_L.gguf b/AceReason-Nemotron-7B.Q3_K_L.gguf new file mode 100644 index 0000000..90c5aa2 --- /dev/null +++ b/AceReason-Nemotron-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a9a9f8029ce699175a490ae77b28d7e5b12127d781c72b232d50e13dc7cb6e +size 4088459392 diff --git a/AceReason-Nemotron-7B.Q3_K_M.gguf b/AceReason-Nemotron-7B.Q3_K_M.gguf new file mode 100644 index 0000000..a67b4f4 --- /dev/null +++ b/AceReason-Nemotron-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8da0f949eb55e5b6bd577a9ead3b7c2f7b3c183340ac56494631322e28aeba7 +size 3808391296 diff --git a/AceReason-Nemotron-7B.Q3_K_S.gguf b/AceReason-Nemotron-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4c03ea4 --- /dev/null +++ b/AceReason-Nemotron-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5abfcd0f994fe77e600f8d6450bb2751ddbae1da67635704d40ba2ab356b34d +size 3492368512 diff --git a/AceReason-Nemotron-7B.Q4_K_M.gguf b/AceReason-Nemotron-7B.Q4_K_M.gguf new file mode 100644 index 0000000..5561c32 --- /dev/null +++ b/AceReason-Nemotron-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a330d95bc0cae57752f80f944ad9d59b8945bd48a1b62e031cb30c2b581d235 +size 4683073664 diff --git a/AceReason-Nemotron-7B.Q4_K_S.gguf b/AceReason-Nemotron-7B.Q4_K_S.gguf new file mode 100644 index 0000000..45f908b --- /dev/null +++ b/AceReason-Nemotron-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f53ddcfda81e6a82817b9c6e5deb86a9c555b5180a861d354cbd2c893a8389b +size 4457769088 diff --git a/AceReason-Nemotron-7B.Q5_K_M.gguf b/AceReason-Nemotron-7B.Q5_K_M.gguf new file mode 100644 index 0000000..8fec4a1 --- /dev/null +++ b/AceReason-Nemotron-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb6b3a303d24052cb01f7264b48299f7f64fdf277747400cdc78d7dccf3ad43 +size 5444831360 diff --git a/AceReason-Nemotron-7B.Q5_K_S.gguf b/AceReason-Nemotron-7B.Q5_K_S.gguf new file mode 100644 index 0000000..ae9cd55 --- /dev/null +++ b/AceReason-Nemotron-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:955fdd26a4d14807fa7cea6c39021d29e9df504b8d0ea60581cf9dfd05cc4c67 +size 5315176576 diff --git a/AceReason-Nemotron-7B.Q6_K.gguf b/AceReason-Nemotron-7B.Q6_K.gguf new file mode 100644 index 0000000..4aae9d8 --- /dev/null +++ b/AceReason-Nemotron-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9fdded4acca382dae38b8d5db3b0b22871785de4f0bf7104a28af3ba4926f6 +size 6254198912 diff --git a/AceReason-Nemotron-7B.Q8_0.gguf b/AceReason-Nemotron-7B.Q8_0.gguf new file mode 100644 index 0000000..a6f4ee7 --- /dev/null +++ b/AceReason-Nemotron-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a914a73f46f53e59aaa7cb357f61b383105cf524167d2fa41c81879ba94aa54 +size 8098525312 diff --git a/AceReason-Nemotron-7B.f16.gguf b/AceReason-Nemotron-7B.f16.gguf new file mode 100644 index 0000000..8e0eeb3 --- /dev/null +++ b/AceReason-Nemotron-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99107c5ec9892edc045f8da05aa3a13e34f491ec36a33c01833b9df464055a4d +size 15237853312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e968e5c --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: nvidia/AceReason-Nemotron-7B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nvidia/AceReason-Nemotron-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AceReason-Nemotron-7B-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/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AceReason-Nemotron-7B-GGUF/resolve/main/AceReason-Nemotron-7B.f16.gguf) | f16 | 15.3 | 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. + +