commit f05846018f0d9866eb2a52c5248b895a0e302e47 Author: ModelHub XC Date: Sat Sep 19 10:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3-8B-VIGGO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e314fc6 --- /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 +Meta-Llama-3-8B-VIGGO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-VIGGO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3-8B-VIGGO.IQ3_M.gguf b/Meta-Llama-3-8B-VIGGO.IQ3_M.gguf new file mode 100644 index 0000000..9f35912 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e327952cef0dfaf14b84c977575af850eb7219fc53c970677634432e775cfb +size 3784823552 diff --git a/Meta-Llama-3-8B-VIGGO.IQ3_S.gguf b/Meta-Llama-3-8B-VIGGO.IQ3_S.gguf new file mode 100644 index 0000000..5140c18 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee80c8cb459a2a6de067cc66e4152253aefd8ee4a31c2bf37890b6bdbd43fa5 +size 3682325248 diff --git a/Meta-Llama-3-8B-VIGGO.IQ3_XS.gguf b/Meta-Llama-3-8B-VIGGO.IQ3_XS.gguf new file mode 100644 index 0000000..d783896 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b088779cb409a2bb903aca666ac02708c344365d284ba2c7f64353e903ab733d +size 3518747392 diff --git a/Meta-Llama-3-8B-VIGGO.IQ4_XS.gguf b/Meta-Llama-3-8B-VIGGO.IQ4_XS.gguf new file mode 100644 index 0000000..1d1cb98 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30f142043d7b0e61f25ba1d1e496ba3bd8fb77e8de589b0f179ec2e20dcb308 +size 4484363008 diff --git a/Meta-Llama-3-8B-VIGGO.Q2_K.gguf b/Meta-Llama-3-8B-VIGGO.Q2_K.gguf new file mode 100644 index 0000000..3852987 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9b125490a5ddd505c43970259f1a6d902fd7f84e037176319a640df6db747a +size 3179131648 diff --git a/Meta-Llama-3-8B-VIGGO.Q3_K_L.gguf b/Meta-Llama-3-8B-VIGGO.Q3_K_L.gguf new file mode 100644 index 0000000..d93ab2e --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84bb58d20ff31ca5bcea736c480d56f0d454dd581bcfefa8f6bcfb3fb410e5f9 +size 4321956608 diff --git a/Meta-Llama-3-8B-VIGGO.Q3_K_M.gguf b/Meta-Llama-3-8B-VIGGO.Q3_K_M.gguf new file mode 100644 index 0000000..8bc09e3 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c06ac2440eda737d1db8b2afdf4fc09d805a3501836d85d64e75f0845b940c +size 4018918144 diff --git a/Meta-Llama-3-8B-VIGGO.Q3_K_S.gguf b/Meta-Llama-3-8B-VIGGO.Q3_K_S.gguf new file mode 100644 index 0000000..223918e --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1ec1c983f78f72050951900919ccccbb0043508e5fdec79233fc49449e0600 +size 3664499456 diff --git a/Meta-Llama-3-8B-VIGGO.Q4_K_M.gguf b/Meta-Llama-3-8B-VIGGO.Q4_K_M.gguf new file mode 100644 index 0000000..96f0334 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12731fe38151be68983f5ed601e67c3b8957975bbe4a89c35e991e087fe1c999 +size 4920734464 diff --git a/Meta-Llama-3-8B-VIGGO.Q4_K_S.gguf b/Meta-Llama-3-8B-VIGGO.Q4_K_S.gguf new file mode 100644 index 0000000..10dd58a --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b6e703836404cb0be358721d4393cacddbf2d13b90e17275f7f9bd3d1767be9 +size 4692669184 diff --git a/Meta-Llama-3-8B-VIGGO.Q5_K_M.gguf b/Meta-Llama-3-8B-VIGGO.Q5_K_M.gguf new file mode 100644 index 0000000..53317ac --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18cd4c5e83ba53e6db7392f764c4fe0e29977665c22d4e3d2b4f82a20d4a42e +size 5732987648 diff --git a/Meta-Llama-3-8B-VIGGO.Q5_K_S.gguf b/Meta-Llama-3-8B-VIGGO.Q5_K_S.gguf new file mode 100644 index 0000000..a940d31 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc8bb1dea6b665bea5fd8b9070d94bf97346146dce0e5fa74eb6b1208600cb6 +size 5599294208 diff --git a/Meta-Llama-3-8B-VIGGO.Q6_K.gguf b/Meta-Llama-3-8B-VIGGO.Q6_K.gguf new file mode 100644 index 0000000..aa07e6e --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:013457470b81b64cfc9451f8ae44a2d9b6a1124c3ce7586aec9a33486cbdbabf +size 6596006656 diff --git a/Meta-Llama-3-8B-VIGGO.Q8_0.gguf b/Meta-Llama-3-8B-VIGGO.Q8_0.gguf new file mode 100644 index 0000000..13d4864 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ecbfeef99923901f9363dd9b4dbd16d49939d8c35548f4475b9e37610159d1 +size 8540771072 diff --git a/Meta-Llama-3-8B-VIGGO.f16.gguf b/Meta-Llama-3-8B-VIGGO.f16.gguf new file mode 100644 index 0000000..af5f758 --- /dev/null +++ b/Meta-Llama-3-8B-VIGGO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa8ffb8fbd82a100fbdcd1ba785b5ce2566d33758b011874275d28365210896 +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f043845 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: asprenger/Meta-Llama-3-8B-VIGGO +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/asprenger/Meta-Llama-3-8B-VIGGO + + +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/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-VIGGO-GGUF/resolve/main/Meta-Llama-3-8B-VIGGO.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. + +