commit 0af53f4f56b88a22c3d31faf1374b53a7ed4dbe3 Author: ModelHub XC Date: Mon Jun 1 13:09:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LL-Iris-V4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..58d6bc2 --- /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 +LL-Iris-V4.f16.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LL-Iris-V4.IQ4_XS.gguf b/LL-Iris-V4.IQ4_XS.gguf new file mode 100644 index 0000000..8bce096 --- /dev/null +++ b/LL-Iris-V4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5ab1b41a5760153a59c6ad350ad2301db29472f8e0adad68cf88f1573bec51 +size 4248357408 diff --git a/LL-Iris-V4.Q2_K.gguf b/LL-Iris-V4.Q2_K.gguf new file mode 100644 index 0000000..55dbec6 --- /dev/null +++ b/LL-Iris-V4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eabef7a55d5f1b1e0bf0983196b3cd388ae28ae0f9d3606bf84f3290956cec9 +size 3014289600 diff --git a/LL-Iris-V4.Q3_K_L.gguf b/LL-Iris-V4.Q3_K_L.gguf new file mode 100644 index 0000000..1a35fcb --- /dev/null +++ b/LL-Iris-V4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e70cafe8f94d84b887414f060afc082d8aceedcc75b685806cb9c415ba278b0 +size 4086663552 diff --git a/LL-Iris-V4.Q3_K_M.gguf b/LL-Iris-V4.Q3_K_M.gguf new file mode 100644 index 0000000..7fe46d4 --- /dev/null +++ b/LL-Iris-V4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b97db9a4ab388591c42ae7b2b2ae6a7b9694f0b57dfa5ba8b6644a3a9571f2 +size 3806595456 diff --git a/LL-Iris-V4.Q3_K_S.gguf b/LL-Iris-V4.Q3_K_S.gguf new file mode 100644 index 0000000..b3ed06d --- /dev/null +++ b/LL-Iris-V4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab86b0e408f7b6895c71393c11c4476c13dbfd93e64898c09b8764ea49e1583 +size 3490572672 diff --git a/LL-Iris-V4.Q4_K_M.gguf b/LL-Iris-V4.Q4_K_M.gguf new file mode 100644 index 0000000..3b4fd22 --- /dev/null +++ b/LL-Iris-V4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35e89a6c3fbc88f4da20690abce84bbd4a295cfc69c96a4e9c2d290ce8b5ad8 +size 4681087872 diff --git a/LL-Iris-V4.Q4_K_S.gguf b/LL-Iris-V4.Q4_K_S.gguf new file mode 100644 index 0000000..a95c809 --- /dev/null +++ b/LL-Iris-V4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abcee58a8fc6b963dabcd6bfb66ab8f127d64a1402c4938644fa13ec19b3b95b +size 4455783296 diff --git a/LL-Iris-V4.Q5_K_M.gguf b/LL-Iris-V4.Q5_K_M.gguf new file mode 100644 index 0000000..9078774 --- /dev/null +++ b/LL-Iris-V4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40cc5266abcf12200046c896b5bec8b8671246dd78e67be4ba58257ecb5ed135 +size 5442666816 diff --git a/LL-Iris-V4.Q5_K_S.gguf b/LL-Iris-V4.Q5_K_S.gguf new file mode 100644 index 0000000..9d00f01 --- /dev/null +++ b/LL-Iris-V4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3db9399a35369844229b4da1036f663efd019009c212ce35c6255c1fb7ef01 +size 5313012032 diff --git a/LL-Iris-V4.Q6_K.gguf b/LL-Iris-V4.Q6_K.gguf new file mode 100644 index 0000000..33fc695 --- /dev/null +++ b/LL-Iris-V4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dae8c896b0a7362cef22962d8256ed8e66f60770ccfaedf81b2224fdc6110a7 +size 6251844448 diff --git a/LL-Iris-V4.Q8_0.gguf b/LL-Iris-V4.Q8_0.gguf new file mode 100644 index 0000000..a9d49d4 --- /dev/null +++ b/LL-Iris-V4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d73b17c7ef431ae3478dd9dbfc673f634d66887d1b1bf90a90383407d4b8d1c +size 8095478176 diff --git a/LL-Iris-V4.f16.gguf b/LL-Iris-V4.f16.gguf new file mode 100644 index 0000000..dcff60e --- /dev/null +++ b/LL-Iris-V4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4b547aabf19a243cbdcd1c1ea4b18927c24d87ed5958f71eb0752e8404362f +size 15232124896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7c895d4 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: LibertysGrit/LL-Iris-V4 +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- autotrain +- text-generation-inference +- text-generation +- peft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/LibertysGrit/LL-Iris-V4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LL-Iris-V4-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/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V4-GGUF/resolve/main/LL-Iris-V4.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. + +