commit 4d7ab8a5ec6474a9054e190cb034452744c15990 Author: ModelHub XC Date: Wed Jun 3 05:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sirena-0.1-llama3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9283c3d --- /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 +sirena-0.1-llama3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sirena-0.1-llama3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..14cec41 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: cazonai/sirena-0.1-llama3-8b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/cazonai/sirena-0.1-llama3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sirena-0.1-llama3-8b-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/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sirena-0.1-llama3-8b-GGUF/resolve/main/sirena-0.1-llama3-8b.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. + + diff --git a/sirena-0.1-llama3-8b.IQ4_XS.gguf b/sirena-0.1-llama3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..b51626c --- /dev/null +++ b/sirena-0.1-llama3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d798f1a99e0830eb81ff9e29aa3d5a4a51a87f2bb3268f11c01d61e92df80aee +size 4484368320 diff --git a/sirena-0.1-llama3-8b.Q2_K.gguf b/sirena-0.1-llama3-8b.Q2_K.gguf new file mode 100644 index 0000000..2fb983f --- /dev/null +++ b/sirena-0.1-llama3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0a2cd1f8e6f03865bc20612170c75d74c5a519279fba59c23f0174ab579a4c +size 3179136960 diff --git a/sirena-0.1-llama3-8b.Q3_K_L.gguf b/sirena-0.1-llama3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..0b617b1 --- /dev/null +++ b/sirena-0.1-llama3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38a19c74e7ba8a20de5b0043ab316c14d2a9c1d29f38de504838ca78329d427 +size 4321961920 diff --git a/sirena-0.1-llama3-8b.Q3_K_M.gguf b/sirena-0.1-llama3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..22dc70c --- /dev/null +++ b/sirena-0.1-llama3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff01ce0531848de34f172f37d5ebaa20b0f2d8d1744cf5480bf8aa3c247d117 +size 4018923456 diff --git a/sirena-0.1-llama3-8b.Q3_K_S.gguf b/sirena-0.1-llama3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..78777e6 --- /dev/null +++ b/sirena-0.1-llama3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db25831a371928b8e2dc522af9027b43d733db384f4e55e5818d78993bf758e6 +size 3664504768 diff --git a/sirena-0.1-llama3-8b.Q4_K_M.gguf b/sirena-0.1-llama3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..aa5595a --- /dev/null +++ b/sirena-0.1-llama3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7cc8ec3099ae4ce6fff731e855a835de1dd3dc944d4036b8eeb391bb972ff9 +size 4920739776 diff --git a/sirena-0.1-llama3-8b.Q4_K_S.gguf b/sirena-0.1-llama3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..1b63fbd --- /dev/null +++ b/sirena-0.1-llama3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f63e681f19ac1be380bc4582501fd820b32824ccc2d3509d9badef001b1a0d +size 4692674496 diff --git a/sirena-0.1-llama3-8b.Q5_K_M.gguf b/sirena-0.1-llama3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..ac85c19 --- /dev/null +++ b/sirena-0.1-llama3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07286a319f841cbc4e3392a4ac4a3ba0e48b0730bac7725fd27d56e8f61cbbe +size 5732992960 diff --git a/sirena-0.1-llama3-8b.Q5_K_S.gguf b/sirena-0.1-llama3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..72c6751 --- /dev/null +++ b/sirena-0.1-llama3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560e0605c095b9bd85c91c6470b6dd03cbb6de246107d2ba6e96a61c3053cdbd +size 5599299520 diff --git a/sirena-0.1-llama3-8b.Q6_K.gguf b/sirena-0.1-llama3-8b.Q6_K.gguf new file mode 100644 index 0000000..f712b32 --- /dev/null +++ b/sirena-0.1-llama3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91ce0b15fba1d4e0fb79d57650ff143737e61d782a48aebe2d2b9bfc66b708b +size 6596011968 diff --git a/sirena-0.1-llama3-8b.Q8_0.gguf b/sirena-0.1-llama3-8b.Q8_0.gguf new file mode 100644 index 0000000..0829bea --- /dev/null +++ b/sirena-0.1-llama3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd58f0c62f2da8fd783bbcded62655fa4bfec3e7a57862e0f55dbb767002094 +size 8540776384 diff --git a/sirena-0.1-llama3-8b.f16.gguf b/sirena-0.1-llama3-8b.f16.gguf new file mode 100644 index 0000000..af18e66 --- /dev/null +++ b/sirena-0.1-llama3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1f78d975f41f288cb0369d2b4b556c72fe455ee45cb4947f7e23bb3b659059 +size 16068896704