commit 22e3e085acfbde7559ab3c05e8db9dfcf124d9b9 Author: ModelHub XC Date: Mon Oct 12 01:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Storm-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d2e0d7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Llama-3.1-Storm-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Storm-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Storm-8B.IQ3_M.gguf b/Llama-3.1-Storm-8B.IQ3_M.gguf new file mode 100644 index 0000000..73cd625 --- /dev/null +++ b/Llama-3.1-Storm-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5fdf3c506f61541d6e3a5a00c450fdc64f80ea425c6b8f1dea3f24ba8f6288 +size 3784824352 diff --git a/Llama-3.1-Storm-8B.IQ3_S.gguf b/Llama-3.1-Storm-8B.IQ3_S.gguf new file mode 100644 index 0000000..72971f6 --- /dev/null +++ b/Llama-3.1-Storm-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c07cd05dcb6683fd67429f6a82a951371a26e87e6df6eca74db28d8d1c74e +size 3682326048 diff --git a/Llama-3.1-Storm-8B.IQ3_XS.gguf b/Llama-3.1-Storm-8B.IQ3_XS.gguf new file mode 100644 index 0000000..df6e2ce --- /dev/null +++ b/Llama-3.1-Storm-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:818840638b2de500236a2774fd241a5f9a5888c69fe62e8b63e7e9454cc1c642 +size 3518748192 diff --git a/Llama-3.1-Storm-8B.IQ4_XS.gguf b/Llama-3.1-Storm-8B.IQ4_XS.gguf new file mode 100644 index 0000000..c5f5180 --- /dev/null +++ b/Llama-3.1-Storm-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027d8f52969b24946fba29c332abed989a9af158660ddea6ddde69925108551b +size 4484363808 diff --git a/Llama-3.1-Storm-8B.Q2_K.gguf b/Llama-3.1-Storm-8B.Q2_K.gguf new file mode 100644 index 0000000..aed89d7 --- /dev/null +++ b/Llama-3.1-Storm-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795b7f1fd0568e7c59a792bc8e605c19799950460ca266bf9be4853c5a04c0d1 +size 3179132448 diff --git a/Llama-3.1-Storm-8B.Q3_K_L.gguf b/Llama-3.1-Storm-8B.Q3_K_L.gguf new file mode 100644 index 0000000..08aa8ba --- /dev/null +++ b/Llama-3.1-Storm-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06bd1426e7bff45d1e839311563f77347285b1896dcc19620bfe826f890b064 +size 4321957408 diff --git a/Llama-3.1-Storm-8B.Q3_K_M.gguf b/Llama-3.1-Storm-8B.Q3_K_M.gguf new file mode 100644 index 0000000..8343f05 --- /dev/null +++ b/Llama-3.1-Storm-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b68740b3d016e0085cf153ddadcf0a81455426e26a7c7c6aa595a15c41abbcb +size 4018918944 diff --git a/Llama-3.1-Storm-8B.Q3_K_S.gguf b/Llama-3.1-Storm-8B.Q3_K_S.gguf new file mode 100644 index 0000000..2461a7a --- /dev/null +++ b/Llama-3.1-Storm-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39686fee443e3a1059a43a25adb0431a4e1547855993560d74a50c010d2fe194 +size 3664500256 diff --git a/Llama-3.1-Storm-8B.Q4_K_M.gguf b/Llama-3.1-Storm-8B.Q4_K_M.gguf new file mode 100644 index 0000000..1f30850 --- /dev/null +++ b/Llama-3.1-Storm-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ac2dd9a572183b215dc1564f32078dedae2b9fd540411beaba23c80faaec27 +size 4920735264 diff --git a/Llama-3.1-Storm-8B.Q4_K_S.gguf b/Llama-3.1-Storm-8B.Q4_K_S.gguf new file mode 100644 index 0000000..75d172b --- /dev/null +++ b/Llama-3.1-Storm-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097446cbd1d389ffcf936e896285c6d7f67d2693ef337c622f30aeb64017e60a +size 4692669984 diff --git a/Llama-3.1-Storm-8B.Q5_K_M.gguf b/Llama-3.1-Storm-8B.Q5_K_M.gguf new file mode 100644 index 0000000..14a5f84 --- /dev/null +++ b/Llama-3.1-Storm-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f35638a5c5ea1a91f08281155fd3b2dbcbb9056e4e7edd7a9acbd5bef47d80 +size 5732988448 diff --git a/Llama-3.1-Storm-8B.Q5_K_S.gguf b/Llama-3.1-Storm-8B.Q5_K_S.gguf new file mode 100644 index 0000000..b245c9b --- /dev/null +++ b/Llama-3.1-Storm-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7661363a49580b99d7714db5cbef30efad48b1b91a37bd20b00a653c83d56cea +size 5599295008 diff --git a/Llama-3.1-Storm-8B.Q6_K.gguf b/Llama-3.1-Storm-8B.Q6_K.gguf new file mode 100644 index 0000000..9a2ec81 --- /dev/null +++ b/Llama-3.1-Storm-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4898f9a9b48ac00ee51b6144767b1d9ae46fccbb2ccccad90ade826882c20e +size 6596007456 diff --git a/Llama-3.1-Storm-8B.Q8_0.gguf b/Llama-3.1-Storm-8B.Q8_0.gguf new file mode 100644 index 0000000..cbf969b --- /dev/null +++ b/Llama-3.1-Storm-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02917473ee40654bfb57758a717ce8e69272a4c9202ab94565acfc32043b1b96 +size 8540771872 diff --git a/Llama-3.1-Storm-8B.f16.gguf b/Llama-3.1-Storm-8B.f16.gguf new file mode 100644 index 0000000..42defc3 --- /dev/null +++ b/Llama-3.1-Storm-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a3c4bda1777cbe0497c19fcba358f66794fd5225f1637577c866b06dcb3a4d +size 16068892192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed3a0d7 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: akjindal53244/Llama-3.1-Storm-8B +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- llama-3.1 +- conversational +- instruction following +- reasoning +- function calling +- mergekit +- finetuning +- axolotl +--- +## About + + + + + + +static quants of https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-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/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Storm-8B-GGUF/resolve/main/Llama-3.1-Storm-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. + +