commit 6e7e137ba12874c612c87e589e636bbda644cc9f Author: ModelHub XC Date: Mon May 25 11:25:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nemo-chatbot-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..98eda7b --- /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-chatbot-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nemo-chatbot-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7ac703e --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: chaerheeon/nemo-chatbot-v2 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/chaerheeon/nemo-chatbot-v2 + + +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-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nemo-chatbot-v2-GGUF/resolve/main/nemo-chatbot-v2.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-chatbot-v2.IQ4_XS.gguf b/nemo-chatbot-v2.IQ4_XS.gguf new file mode 100644 index 0000000..d1b2ae0 --- /dev/null +++ b/nemo-chatbot-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a653273568caf7f4c9a11556f08d5a4a8781db691974d601b85067e79ee3c183 +size 2279624352 diff --git a/nemo-chatbot-v2.Q2_K.gguf b/nemo-chatbot-v2.Q2_K.gguf new file mode 100644 index 0000000..1144e1e --- /dev/null +++ b/nemo-chatbot-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad96019ab3ad1b95943a14cd68239a517d58e30298483bf728d603efbc6b6bb7 +size 1729162912 diff --git a/nemo-chatbot-v2.Q3_K_L.gguf b/nemo-chatbot-v2.Q3_K_L.gguf new file mode 100644 index 0000000..657c413 --- /dev/null +++ b/nemo-chatbot-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb991baa0f003f5f5197152573513159e7a87ba9353906401a7c4a51baf81df +size 2236083872 diff --git a/nemo-chatbot-v2.Q3_K_M.gguf b/nemo-chatbot-v2.Q3_K_M.gguf new file mode 100644 index 0000000..a5f6e56 --- /dev/null +++ b/nemo-chatbot-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f3628c5f7e2e8eb538c692c1ba1d809647fdbe28e1fbe2f13e21fbca50c6af +size 2098458272 diff --git a/nemo-chatbot-v2.Q3_K_S.gguf b/nemo-chatbot-v2.Q3_K_S.gguf new file mode 100644 index 0000000..f4b21f0 --- /dev/null +++ b/nemo-chatbot-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cb45cac10b0047dc9c875b4d7892eaa5a7a4a43f509156f1d838dc044c8e21 +size 1937362592 diff --git a/nemo-chatbot-v2.Q4_K_M.gguf b/nemo-chatbot-v2.Q4_K_M.gguf new file mode 100644 index 0000000..d93b64c --- /dev/null +++ b/nemo-chatbot-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ad0ac7e83493219b06cb1bc6995b3eed3668464d17c438adf36ee3acebac57 +size 2489892512 diff --git a/nemo-chatbot-v2.Q4_K_S.gguf b/nemo-chatbot-v2.Q4_K_S.gguf new file mode 100644 index 0000000..1b08474 --- /dev/null +++ b/nemo-chatbot-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4159a64f7ddcf5a80a85a52d5452cd9324dfbd510e2796015e9ecc1654d5c27e +size 2377928352 diff --git a/nemo-chatbot-v2.Q5_K_M.gguf b/nemo-chatbot-v2.Q5_K_M.gguf new file mode 100644 index 0000000..83f1e53 --- /dev/null +++ b/nemo-chatbot-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb448b34ec82d3eecbc13676c9f4fc165ed8101e6b7d048a62acb11c3e1cd41 +size 2829696672 diff --git a/nemo-chatbot-v2.Q5_K_S.gguf b/nemo-chatbot-v2.Q5_K_S.gguf new file mode 100644 index 0000000..a15a70a --- /dev/null +++ b/nemo-chatbot-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9457d9e0ebd1daee73961971790436a7fcc7c02a4a518dd5a7a3207f9583a052 +size 2764590752 diff --git a/nemo-chatbot-v2.Q6_K.gguf b/nemo-chatbot-v2.Q6_K.gguf new file mode 100644 index 0000000..fab659b --- /dev/null +++ b/nemo-chatbot-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ee50533c113ac250f88e98bbc98ff3ad6917cd41a20262601ea3e2b5ea2836 +size 3190738592 diff --git a/nemo-chatbot-v2.Q8_0.gguf b/nemo-chatbot-v2.Q8_0.gguf new file mode 100644 index 0000000..43b294b --- /dev/null +++ b/nemo-chatbot-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718a491b65b4a796e9e0d9b95d9424bbb279296a8865bc7e45241b3d7be073f4 +size 4130400672 diff --git a/nemo-chatbot-v2.f16.gguf b/nemo-chatbot-v2.f16.gguf new file mode 100644 index 0000000..2be4572 --- /dev/null +++ b/nemo-chatbot-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384f30c2aed54f016209561f57b6fbceee1950acb45863e1387f84c05c40c36e +size 7767802272