commit 4eb90205f7af2a73ce408c6460a6fcd00b90edfb Author: ModelHub XC Date: Sat Jun 13 06:06:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nemo-multitask-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a9d665e --- /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 +nemo-multitask-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nemo-multitask-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..537b624 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: chaerheeon/nemo-multitask-v3 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/chaerheeon/nemo-multitask-v3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#nemo-multitask-v3-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/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nemo-multitask-v3-GGUF/resolve/main/nemo-multitask-v3.f16.gguf) | f16 | 7.9 | 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. + + diff --git a/nemo-multitask-v3.IQ4_XS.gguf b/nemo-multitask-v3.IQ4_XS.gguf new file mode 100644 index 0000000..01b4264 --- /dev/null +++ b/nemo-multitask-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2024ca92178054be4d532bc836b7119a8f62d2f4d6dc2699e8b0362640849c3f +size 2279625984 diff --git a/nemo-multitask-v3.Q2_K.gguf b/nemo-multitask-v3.Q2_K.gguf new file mode 100644 index 0000000..1cf4b97 --- /dev/null +++ b/nemo-multitask-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b70b3fef922d29c7e9a1ae53c4b608f0ea8da249bc99039ae76ff99e9fba28 +size 1729164544 diff --git a/nemo-multitask-v3.Q3_K_L.gguf b/nemo-multitask-v3.Q3_K_L.gguf new file mode 100644 index 0000000..ec3f834 --- /dev/null +++ b/nemo-multitask-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2fc2db3a6070458dfda6da24fbcb0a003dfd44be0557806ef7818c2095783d5 +size 2236085504 diff --git a/nemo-multitask-v3.Q3_K_M.gguf b/nemo-multitask-v3.Q3_K_M.gguf new file mode 100644 index 0000000..3a09503 --- /dev/null +++ b/nemo-multitask-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14dd7ff20d7fc91c9b3d08cdd49c202adc571368e5b97c89bc6e220566f468b0 +size 2098459904 diff --git a/nemo-multitask-v3.Q3_K_S.gguf b/nemo-multitask-v3.Q3_K_S.gguf new file mode 100644 index 0000000..c5f9234 --- /dev/null +++ b/nemo-multitask-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92915c62ac5380dc9ed3347e7700f683c0f6989be38996853d7816b787624149 +size 1937364224 diff --git a/nemo-multitask-v3.Q4_K_M.gguf b/nemo-multitask-v3.Q4_K_M.gguf new file mode 100644 index 0000000..261963e --- /dev/null +++ b/nemo-multitask-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d874b55903499c0ce316fff1e1edaa416811837b2f2bea20d5b48da1b17abc8 +size 2489894144 diff --git a/nemo-multitask-v3.Q4_K_S.gguf b/nemo-multitask-v3.Q4_K_S.gguf new file mode 100644 index 0000000..58aac81 --- /dev/null +++ b/nemo-multitask-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37445e17f8552429134aadb02cb7a75c3deec784ea846661f3ec26ebe7685cea +size 2377929984 diff --git a/nemo-multitask-v3.Q5_K_M.gguf b/nemo-multitask-v3.Q5_K_M.gguf new file mode 100644 index 0000000..e2210ba --- /dev/null +++ b/nemo-multitask-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e1212515322cd01c49723fc57fb7410897439be1eaea1f0ebad4daec7e46a0 +size 2829698304 diff --git a/nemo-multitask-v3.Q5_K_S.gguf b/nemo-multitask-v3.Q5_K_S.gguf new file mode 100644 index 0000000..762b0bf --- /dev/null +++ b/nemo-multitask-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc60cf3c6e72f31b5024aa0f681ae6a3980f51dcbf5d3075e4fede96af3858c5 +size 2764592384 diff --git a/nemo-multitask-v3.Q6_K.gguf b/nemo-multitask-v3.Q6_K.gguf new file mode 100644 index 0000000..fe45291 --- /dev/null +++ b/nemo-multitask-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a0aefeea2742b4957904d065584cdfdb8dd06b7012978ae4b458f831f83320 +size 3190740224 diff --git a/nemo-multitask-v3.Q8_0.gguf b/nemo-multitask-v3.Q8_0.gguf new file mode 100644 index 0000000..b914bca --- /dev/null +++ b/nemo-multitask-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288cad690d8f9f5fe88bde7fbbdab3800ca74da60cf04237070fc2f92fdf0d4f +size 4130402304 diff --git a/nemo-multitask-v3.f16.gguf b/nemo-multitask-v3.f16.gguf new file mode 100644 index 0000000..8a30278 --- /dev/null +++ b/nemo-multitask-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd19d4059f96fad001a90869e84b1536d96dae683e66c5baad7322598acb39d +size 7767803904