commit cc7e72d8641c7e48c5d3257ca4ff886ebc7fc981 Author: ModelHub XC Date: Wed Aug 5 10:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-tofutune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6468fe3 --- /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 +llama3-8b-tofutune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-tofutune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b63e60e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: simonbutt/llama3-8b-tofutune +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/simonbutt/llama3-8b-tofutune + + +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/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-tofutune-GGUF/resolve/main/llama3-8b-tofutune.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama3-8b-tofutune.IQ4_XS.gguf b/llama3-8b-tofutune.IQ4_XS.gguf new file mode 100644 index 0000000..ff3aa43 --- /dev/null +++ b/llama3-8b-tofutune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7492e39c81660f74606b22a58e95e79f2b809511472f447c552dee3dd3631e +size 4484363296 diff --git a/llama3-8b-tofutune.Q2_K.gguf b/llama3-8b-tofutune.Q2_K.gguf new file mode 100644 index 0000000..7f142e4 --- /dev/null +++ b/llama3-8b-tofutune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e368fe05f5b8e1a09f562be3f0d61cf64003bb3cbb1da4a5a006b0a2679a578 +size 3179131936 diff --git a/llama3-8b-tofutune.Q3_K_L.gguf b/llama3-8b-tofutune.Q3_K_L.gguf new file mode 100644 index 0000000..57d31fd --- /dev/null +++ b/llama3-8b-tofutune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af11c587c08e285ac8005ba7babd2e8807123ac2c027bf8366d2ab8df8e530a2 +size 4321956896 diff --git a/llama3-8b-tofutune.Q3_K_M.gguf b/llama3-8b-tofutune.Q3_K_M.gguf new file mode 100644 index 0000000..c3aac8d --- /dev/null +++ b/llama3-8b-tofutune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b772a8a0da992d47b3408436e193ec33e42f50abd869ba142315653da221d16 +size 4018918432 diff --git a/llama3-8b-tofutune.Q3_K_S.gguf b/llama3-8b-tofutune.Q3_K_S.gguf new file mode 100644 index 0000000..a505ddd --- /dev/null +++ b/llama3-8b-tofutune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2ed17c47cb5a3a47b4969ef92e5d5e3e35cf069c70c0398e51f2ee712ded02 +size 3664499744 diff --git a/llama3-8b-tofutune.Q4_K_M.gguf b/llama3-8b-tofutune.Q4_K_M.gguf new file mode 100644 index 0000000..f33ceae --- /dev/null +++ b/llama3-8b-tofutune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9de896de2619415f9788c0ceb1b527e90c05effaddbbd76c742a9729c9e40dc +size 4920734752 diff --git a/llama3-8b-tofutune.Q4_K_S.gguf b/llama3-8b-tofutune.Q4_K_S.gguf new file mode 100644 index 0000000..cebfd46 --- /dev/null +++ b/llama3-8b-tofutune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:483b48171147b120d04c52848be1b0c06633e05773316605386c1c29578685d2 +size 4692669472 diff --git a/llama3-8b-tofutune.Q5_K_M.gguf b/llama3-8b-tofutune.Q5_K_M.gguf new file mode 100644 index 0000000..93f9f8a --- /dev/null +++ b/llama3-8b-tofutune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad59273dbaa2e93f5e7226330c40df0f8f29e7d3f870346062723a6a295c99f +size 5732987936 diff --git a/llama3-8b-tofutune.Q5_K_S.gguf b/llama3-8b-tofutune.Q5_K_S.gguf new file mode 100644 index 0000000..d96fa13 --- /dev/null +++ b/llama3-8b-tofutune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39232e080f26691fc4c1d3c63376a855e406a8deb273fa6c0d38b5a4eafe3f1 +size 5599294496 diff --git a/llama3-8b-tofutune.Q6_K.gguf b/llama3-8b-tofutune.Q6_K.gguf new file mode 100644 index 0000000..434672a --- /dev/null +++ b/llama3-8b-tofutune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4e41db2fba2356ac943bb429b3cda6c7eea31f22047b7eeaf459794dfa2445 +size 6596006944 diff --git a/llama3-8b-tofutune.Q8_0.gguf b/llama3-8b-tofutune.Q8_0.gguf new file mode 100644 index 0000000..c9de82f --- /dev/null +++ b/llama3-8b-tofutune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:082dd7400820c219fdf4aa69025bdb85347e3cfd5534b63ef0295de5c01f8ddc +size 8540771360 diff --git a/llama3-8b-tofutune.f16.gguf b/llama3-8b-tofutune.f16.gguf new file mode 100644 index 0000000..ec4c21b --- /dev/null +++ b/llama3-8b-tofutune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a6c517d7d8852d2dde6941055f79bfc133a26ef2344c7d0f98049bd956fd83 +size 16068891680