commit 817b5ccf5fb42ca853966c0621a55ce1f14d3766 Author: ModelHub XC Date: Tue Aug 4 09:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..65450bf --- /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 +Llama_3.1_8b_Stormeder_v1.04.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Stormeder_v1.04.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Stormeder_v1.04.IQ4_XS.gguf b/Llama_3.1_8b_Stormeder_v1.04.IQ4_XS.gguf new file mode 100644 index 0000000..2940bf5 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a34fe71adcf52e5f558355026c8fd2b7de89fc12886a9939a8352c6b5401f8 +size 4484364576 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q2_K.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q2_K.gguf new file mode 100644 index 0000000..8cd1cdf --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59d9bf04105c58b89af8065179239836883993ffb95b851aa9645d9b04cd53c +size 3179133216 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q3_K_L.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q3_K_L.gguf new file mode 100644 index 0000000..087a5dd --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32472e25a715881cf5f17ec1b03a147c60740403bbb29fc1be9a0025665f54ff +size 4321958176 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q3_K_M.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q3_K_M.gguf new file mode 100644 index 0000000..4685f6b --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6436cefee0305ef0996c686ca8d0bc13c895d0cb25bd74e814ba60501c5e1a2b +size 4018919712 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q3_K_S.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q3_K_S.gguf new file mode 100644 index 0000000..a1ac373 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e88167f827e45bcd39c740aed2201016d13b741f1bab9d172207b54d8178fd +size 3664501024 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q4_K_M.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q4_K_M.gguf new file mode 100644 index 0000000..4de22f9 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7712d1d48ce006ae14521f8f077e13d854d029eeee05f0426f4a5d8e14bfc1 +size 4920736032 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q4_K_S.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q4_K_S.gguf new file mode 100644 index 0000000..6703237 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e73604222fa9cb1730e14bea4eed16729cac00023c5443bc6ec714cebaaa966 +size 4692670752 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q5_K_M.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q5_K_M.gguf new file mode 100644 index 0000000..9ca6479 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bba854cc670eab850c39a30c249b22507400774c3b1b8929ca1bdf7404d7b5 +size 5732989216 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q5_K_S.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q5_K_S.gguf new file mode 100644 index 0000000..3c8aa88 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c6c6cb6bb5201d78c332e4b7f307e499284d78535a8ba5efd5ab38f943a1c6 +size 5599295776 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q6_K.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q6_K.gguf new file mode 100644 index 0000000..33ad7fa --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197123746396abc3f6de788e48e245e4fa392804f1e022bfb427a0e929c98246 +size 6596008224 diff --git a/Llama_3.1_8b_Stormeder_v1.04.Q8_0.gguf b/Llama_3.1_8b_Stormeder_v1.04.Q8_0.gguf new file mode 100644 index 0000000..1144858 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29c0f67bf637c8b47b977d5cc6671d5ba6be6e9feb9f1aa695656930e48c6e7 +size 8540772640 diff --git a/Llama_3.1_8b_Stormeder_v1.04.f16.gguf b/Llama_3.1_8b_Stormeder_v1.04.f16.gguf new file mode 100644 index 0000000..37b2b71 --- /dev/null +++ b/Llama_3.1_8b_Stormeder_v1.04.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce4c2ea3266f84d3c3d1d9d1813090f9d4ebd48201a339daeefe56af8d0c310 +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..724fb2a --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Stormeder_v1.04 +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.1_8b_Stormeder_v1.04 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-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_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Stormeder_v1.04-GGUF/resolve/main/Llama_3.1_8b_Stormeder_v1.04.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. + +