commit 39f8a114ee901d89efbebbc72c01e35a230271cb Author: ModelHub XC Date: Thu Jun 25 15:33:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5ea4f93 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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 +L3.1-Niitorm-8B-LATCOSx2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Niitorm-8B-LATCOSx2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Niitorm-8B-LATCOSx2.IQ4_XS.gguf b/L3.1-Niitorm-8B-LATCOSx2.IQ4_XS.gguf new file mode 100644 index 0000000..a4d301f --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:681dd92fcb90d193635cec13e4dba00be8c2cb2467ce8c14fca381867c594e86 +size 4484367744 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q2_K.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q2_K.gguf new file mode 100644 index 0000000..31280d0 --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30622c0bfe82606ffddfa06050525334c787ad0fb437c601f8cdda00706bee73 +size 3179136384 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q3_K_L.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q3_K_L.gguf new file mode 100644 index 0000000..444e75c --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89415c09283ea740bbd15909d2c36181c7ae37bd75c368ded89d003511f734c +size 4321961344 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q3_K_M.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q3_K_M.gguf new file mode 100644 index 0000000..92aee4a --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beec35c9fbc5e298a067768c6fb0320045b1dd04d2db26c2329c8636b21ba11e +size 4018922880 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q3_K_S.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q3_K_S.gguf new file mode 100644 index 0000000..7ab0eeb --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f394d4f99a8f23319fabce3b668dab3407cbd230412cd10086876ef968552ba +size 3664504192 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q4_K_M.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q4_K_M.gguf new file mode 100644 index 0000000..b5b0793 --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9fd6eaf75d66bdf5621afb88b2c17c77ecc9cf788042db61d6a23c7e5ad7c4 +size 4920739200 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q4_K_S.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q4_K_S.gguf new file mode 100644 index 0000000..e154646 --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32795da9a5005b7f667617fee51e9c4e94f383da4fbc04079a73e9e5ac020edd +size 4692673920 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q5_K_M.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q5_K_M.gguf new file mode 100644 index 0000000..9ae5d49 --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f10a01b872cca95b7af711fabe7b8dddd953d0535238d115678045e67c31775 +size 5732992384 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q5_K_S.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q5_K_S.gguf new file mode 100644 index 0000000..ae51abc --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd8d8580d8a3b792284d2fcd40ca8f1d011aecd0372110fbd8bf9ee6ac91e44 +size 5599298944 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q6_K.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q6_K.gguf new file mode 100644 index 0000000..f37d86b --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bba4a21569eca5a284fd8213d642b37e53955d2a0d827e5793a47bf9aec0763 +size 6596011392 diff --git a/L3.1-Niitorm-8B-LATCOSx2.Q8_0.gguf b/L3.1-Niitorm-8B-LATCOSx2.Q8_0.gguf new file mode 100644 index 0000000..5bac022 --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276160e9973fdd3bb450ad7d3ba970b96dc7f877a82b430b6f89098c49239333 +size 8540775808 diff --git a/L3.1-Niitorm-8B-LATCOSx2.f16.gguf b/L3.1-Niitorm-8B-LATCOSx2.f16.gguf new file mode 100644 index 0000000..0e62f8f --- /dev/null +++ b/L3.1-Niitorm-8B-LATCOSx2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a9692427518fb3f3c9fec7f167b2dffdf6b5713401ce2d625668e978b9d50d +size 16068896128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a4dae35 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: v000000/L3.1-Niitorm-8B-LATCOSx2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/v000000/L3.1-Niitorm-8B-LATCOSx2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.1-Niitorm-8B-LATCOSx2-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/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Niitorm-8B-LATCOSx2-GGUF/resolve/main/L3.1-Niitorm-8B-LATCOSx2.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. + +