commit 739c2699e3e5cb941238253f038cb11d67fcfa89 Author: ModelHub XC Date: Wed Jun 3 16:06:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LL-Iris-V5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d38a5a0 --- /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-V5.f16.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LL-Iris-V5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LL-Iris-V5.IQ4_XS.gguf b/LL-Iris-V5.IQ4_XS.gguf new file mode 100644 index 0000000..f0614ba --- /dev/null +++ b/LL-Iris-V5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b257e414d993a7eb8de773796bd275faab6e92bf6bca3517750436ef465c2132 +size 4248357408 diff --git a/LL-Iris-V5.Q2_K.gguf b/LL-Iris-V5.Q2_K.gguf new file mode 100644 index 0000000..b2adcd8 --- /dev/null +++ b/LL-Iris-V5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e536172d7387794efe9bfb9f2f49068f63a001bdf6d6c7884f8dfe2696d2a1 +size 3014289600 diff --git a/LL-Iris-V5.Q3_K_L.gguf b/LL-Iris-V5.Q3_K_L.gguf new file mode 100644 index 0000000..17230d1 --- /dev/null +++ b/LL-Iris-V5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b9db1447528abe69f64b4fc1712389d3fa861d1815bfb12400e5eafb362b2c +size 4086663552 diff --git a/LL-Iris-V5.Q3_K_M.gguf b/LL-Iris-V5.Q3_K_M.gguf new file mode 100644 index 0000000..eb63344 --- /dev/null +++ b/LL-Iris-V5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91708e31292b76793ddbb3e31875faa3aa4a923ff9efda7a8d9d83ed5ae05af6 +size 3806595456 diff --git a/LL-Iris-V5.Q3_K_S.gguf b/LL-Iris-V5.Q3_K_S.gguf new file mode 100644 index 0000000..0e2e492 --- /dev/null +++ b/LL-Iris-V5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:620216de1286c1f47c41afd340f37a964c745d0d19519d7c0b1c08fa958c6b8d +size 3490572672 diff --git a/LL-Iris-V5.Q4_K_M.gguf b/LL-Iris-V5.Q4_K_M.gguf new file mode 100644 index 0000000..fd1525e --- /dev/null +++ b/LL-Iris-V5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f82d46145c7730ca639540fbd40af4fbefbd1d5643ae386ea56775f42a912d +size 4681087872 diff --git a/LL-Iris-V5.Q4_K_S.gguf b/LL-Iris-V5.Q4_K_S.gguf new file mode 100644 index 0000000..6f13043 --- /dev/null +++ b/LL-Iris-V5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d553885da1cce6f0f757382d79e5118ce9ca26ddfbcca223909e58abc9dbe0 +size 4455783296 diff --git a/LL-Iris-V5.Q5_K_M.gguf b/LL-Iris-V5.Q5_K_M.gguf new file mode 100644 index 0000000..6d49dac --- /dev/null +++ b/LL-Iris-V5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af3caf982a124799c4a01c1accb0ec92d7f0a22df1013560bcde0a93a26711be +size 5442666816 diff --git a/LL-Iris-V5.Q5_K_S.gguf b/LL-Iris-V5.Q5_K_S.gguf new file mode 100644 index 0000000..19cbb6c --- /dev/null +++ b/LL-Iris-V5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8a9083279dba2273f9f9af16700e4ec4bfb0ca7e3d8a24d1a847bd24c976b0 +size 5313012032 diff --git a/LL-Iris-V5.Q6_K.gguf b/LL-Iris-V5.Q6_K.gguf new file mode 100644 index 0000000..c19a463 --- /dev/null +++ b/LL-Iris-V5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bde611d6a4abeab4057a42e33ca38ace1ff139583f0b4b8934879f7d66633d +size 6251844448 diff --git a/LL-Iris-V5.Q8_0.gguf b/LL-Iris-V5.Q8_0.gguf new file mode 100644 index 0000000..2fb8c1a --- /dev/null +++ b/LL-Iris-V5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fef422051d02b0aa0c08de393a03ec69139b59e72883976eeb09a5b28cbfeb +size 8095478176 diff --git a/LL-Iris-V5.f16.gguf b/LL-Iris-V5.f16.gguf new file mode 100644 index 0000000..f8b7ce2 --- /dev/null +++ b/LL-Iris-V5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9867f4f72a5a8d1480aa4ab779ca3ea19129e1e287eeae8522c27d12fd588739 +size 15232124896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7277824 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: LibertysGrit/LL-Iris-V1 +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-V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LL-Iris-V5-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-V5-GGUF/resolve/main/LL-Iris-V5.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LL-Iris-V5-GGUF/resolve/main/LL-Iris-V5.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. + +