commit 7de5aca98858cd243685075e9867afb9609a4015 Author: ModelHub XC Date: Tue Jun 16 03:02:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-FlashNorm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75409ae --- /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-FlashNorm.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-FlashNorm.IQ4_XS.gguf b/Llama-3.1-8B-FlashNorm.IQ4_XS.gguf new file mode 100644 index 0000000..0edfa1c --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156c91173b5efa51b176eec939b6717d29ba582b77b7941c8c06c2e5cb6f015e +size 4484363616 diff --git a/Llama-3.1-8B-FlashNorm.Q2_K.gguf b/Llama-3.1-8B-FlashNorm.Q2_K.gguf new file mode 100644 index 0000000..7bfc678 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d294d0f1f186ece96af47ae6f9eda17ca23b222519abcc15cd87e5b8e37c1351 +size 3179132256 diff --git a/Llama-3.1-8B-FlashNorm.Q3_K_L.gguf b/Llama-3.1-8B-FlashNorm.Q3_K_L.gguf new file mode 100644 index 0000000..04dd1c0 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbbad0f7cc6386c29bbc266b005da0c6df06149b153372a9eeeae1764f0af7b +size 4321957216 diff --git a/Llama-3.1-8B-FlashNorm.Q3_K_M.gguf b/Llama-3.1-8B-FlashNorm.Q3_K_M.gguf new file mode 100644 index 0000000..83d0cd9 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e5c57f90651c25ae7e1939cfcf8360f1f0a5de3f46635e469888a30b228351 +size 4018918752 diff --git a/Llama-3.1-8B-FlashNorm.Q3_K_S.gguf b/Llama-3.1-8B-FlashNorm.Q3_K_S.gguf new file mode 100644 index 0000000..ef02a26 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed3ea5b1fb51e7eb28c5f7fb2be13bc50814a14369414d19e2ec42b19ea2b62 +size 3664500064 diff --git a/Llama-3.1-8B-FlashNorm.Q4_K_M.gguf b/Llama-3.1-8B-FlashNorm.Q4_K_M.gguf new file mode 100644 index 0000000..e83ae27 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db00ebbb328f7a53a8ef688542a0f22b2015ba5301321e8413405e8597fe7fa3 +size 4920735072 diff --git a/Llama-3.1-8B-FlashNorm.Q4_K_S.gguf b/Llama-3.1-8B-FlashNorm.Q4_K_S.gguf new file mode 100644 index 0000000..fa01c35 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586de4b8e4b2bee23e9660f19b7437e8539275ef7c033f7645b3928df3ef475c +size 4692669792 diff --git a/Llama-3.1-8B-FlashNorm.Q5_K_M.gguf b/Llama-3.1-8B-FlashNorm.Q5_K_M.gguf new file mode 100644 index 0000000..f682e9d --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7100250a3f1491d140833e933e79886cb7eed7cc2bfb6e913c6b349ff238c6 +size 5732988256 diff --git a/Llama-3.1-8B-FlashNorm.Q5_K_S.gguf b/Llama-3.1-8B-FlashNorm.Q5_K_S.gguf new file mode 100644 index 0000000..35de093 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae2395f1d13496627ffbbf1a42b97e6857809bcb0a4e1a3b9e03e6d9d9119e6 +size 5599294816 diff --git a/Llama-3.1-8B-FlashNorm.Q6_K.gguf b/Llama-3.1-8B-FlashNorm.Q6_K.gguf new file mode 100644 index 0000000..e18df16 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab09b61fbace753ca8c625c653537dbf644a1c4e4a9d47a6f97dcb9db991125 +size 6596007264 diff --git a/Llama-3.1-8B-FlashNorm.Q8_0.gguf b/Llama-3.1-8B-FlashNorm.Q8_0.gguf new file mode 100644 index 0000000..c3d2af2 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77309db33e0337180e5c387ec63d5e9369744b104d6a2c34591a380ea35ac411 +size 8540771680 diff --git a/Llama-3.1-8B-FlashNorm.f16.gguf b/Llama-3.1-8B-FlashNorm.f16.gguf new file mode 100644 index 0000000..d8ba74e --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a86bbf5385c5f199b69974ab7e6a0b73e45ca1b016a06a51f91ae6c55f34bc +size 16068892000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..265875a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: open-machine/Llama-3.1-8B-FlashNorm-test +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- flashnorm +- transformer-tricks +- efficient-inference +--- +## About + + + + + + + + + +static quants of https://huggingface.co/open-machine/Llama-3.1-8B-FlashNorm-test + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-FlashNorm-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-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-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.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. + +