commit 24277f14aa2104c0b18b7ab7d7860ed67d8ffaa2 Author: ModelHub XC Date: Tue Jun 16 02:42:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nous-1-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6298a2e --- /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 +Nous-1-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nous-1-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nous-1-4B.IQ4_XS.gguf b/Nous-1-4B.IQ4_XS.gguf new file mode 100644 index 0000000..9781ced --- /dev/null +++ b/Nous-1-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb99a79f833b2ce7931621e0c4cb8986b6c8c820b0cc390ddff98565695f542c +size 2286318464 diff --git a/Nous-1-4B.Q2_K.gguf b/Nous-1-4B.Q2_K.gguf new file mode 100644 index 0000000..fc7ece9 --- /dev/null +++ b/Nous-1-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3238639bfaa7a196717f3baf1c3fac9c565326279d6af136914472a82cc0bbc8 +size 1669501824 diff --git a/Nous-1-4B.Q3_K_L.gguf b/Nous-1-4B.Q3_K_L.gguf new file mode 100644 index 0000000..d3fcf0d --- /dev/null +++ b/Nous-1-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a59624ebc7223d5b6fd3d865dfde20292109f8bf58411e1fe89ac0cbacd0e8f3 +size 2239787904 diff --git a/Nous-1-4B.Q3_K_M.gguf b/Nous-1-4B.Q3_K_M.gguf new file mode 100644 index 0000000..423c2ba --- /dev/null +++ b/Nous-1-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53b1a92092d9209233ff511c44db4884848be62b81028f21baf06805ef1355a +size 2075620224 diff --git a/Nous-1-4B.Q3_K_S.gguf b/Nous-1-4B.Q3_K_S.gguf new file mode 100644 index 0000000..ee54ee8 --- /dev/null +++ b/Nous-1-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bc8809a377cd71b34ad388d95e40fd7a61ceca05502504637d4f12e23d3beb +size 1886999424 diff --git a/Nous-1-4B.Q4_K_M.gguf b/Nous-1-4B.Q4_K_M.gguf new file mode 100644 index 0000000..09701f3 --- /dev/null +++ b/Nous-1-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1ebd05130769004a2e97633d2907976f050d32ab024dbf2a849b6d2e116e98 +size 2497282944 diff --git a/Nous-1-4B.Q4_K_S.gguf b/Nous-1-4B.Q4_K_S.gguf new file mode 100644 index 0000000..e12d322 --- /dev/null +++ b/Nous-1-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d51569399c8a0dfa60bfbd2a02392b327723ed0bdf13bb9fa9bb965318a0aa +size 2383311744 diff --git a/Nous-1-4B.Q5_K_M.gguf b/Nous-1-4B.Q5_K_M.gguf new file mode 100644 index 0000000..e692b6a --- /dev/null +++ b/Nous-1-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403385c751dac7215f765f0ea5ce78b71f74f0909f221d91e4029e57fc379ebb +size 2889515904 diff --git a/Nous-1-4B.Q5_K_S.gguf b/Nous-1-4B.Q5_K_S.gguf new file mode 100644 index 0000000..78d5f7a --- /dev/null +++ b/Nous-1-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fb78d3bc7e3e01b5b12e9072a315c3d82d650c6b169ed3d7faa6fd26868ac7 +size 2823713664 diff --git a/Nous-1-4B.Q6_K.gguf b/Nous-1-4B.Q6_K.gguf new file mode 100644 index 0000000..2a04240 --- /dev/null +++ b/Nous-1-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe356f7e5a2fab3698f2256e7fc80792667a7bb55bb0ce81b940bcd64b42bc62 +size 3306263424 diff --git a/Nous-1-4B.Q8_0.gguf b/Nous-1-4B.Q8_0.gguf new file mode 100644 index 0000000..a3b37cb --- /dev/null +++ b/Nous-1-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948d5552a4ee526104dc0453625e2ecae1bc2bc65a217347bbf79ad2a66647f7 +size 4280407424 diff --git a/Nous-1-4B.f16.gguf b/Nous-1-4B.f16.gguf new file mode 100644 index 0000000..dd3739a --- /dev/null +++ b/Nous-1-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a04f1b571e851c6e3e368fd9adf22054246ac0c1c25ec1adb7a63ee78e06615 +size 8051287424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c178cf0 --- /dev/null +++ b/README.md @@ -0,0 +1,185 @@ +--- +base_model: Loom-Labs/Apollo-1-4B +language: +- en +- fr +- pt +- de +- ro +- sv +- da +- bg +- ru +- cs +- el +- uk +- es +- nl +- sk +- hr +- pl +- lt +- nb +- nn +- fa +- sl +- gu +- lv +- it +- oc +- ne +- mr +- be +- sr +- lb +- vec +- as +- cy +- szl +- ast +- hne +- awa +- mai +- bho +- sd +- ga +- fo +- hi +- pa +- bn +- or +- tg +- yi +- lmo +- lij +- scn +- fur +- sc +- gl +- ca +- is +- sq +- li +- prs +- af +- mk +- si +- ur +- mag +- bs +- hy +- zh +- yue +- my +- ar +- he +- mt +- id +- ms +- tl +- ceb +- jv +- su +- min +- ban +- pag +- ilo +- war +- ta +- te +- kn +- ml +- tr +- az +- uz +- kk +- ba +- tt +- th +- lo +- fi +- et +- hu +- vi +- km +- ja +- ko +- ka +- eu +- ht +- pap +- kea +- tpi +- sw +library_name: transformers +license: other +license_link: https://huggingface.co/apexion-ai/Nous-V1-8B/blob/main/LICENSE.md +license_name: anvdl-1.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + +static quants of https://huggingface.co/Loom-Labs/Apollo-1-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nous-1-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nous-1-4B-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/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nous-1-4B-GGUF/resolve/main/Nous-1-4B.f16.gguf) | f16 | 8.2 | 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. + +