commit 9e936ada7110563d824f7f089f0f8ca46051b2e3 Author: ModelHub XC Date: Mon May 11 11:15:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FunLLama3-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60467ca --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FunLLama3-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FunLLama3-8B.i1-IQ1_M.gguf b/FunLLama3-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..660041f --- /dev/null +++ b/FunLLama3-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc8fed1f43cb63c0b5825d96d660bc932472b510f54f2df74e55fcb88534f1ed +size 2161972160 diff --git a/FunLLama3-8B.i1-IQ1_S.gguf b/FunLLama3-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..bd229d9 --- /dev/null +++ b/FunLLama3-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30d3eb18ecca19cf3fc20d89bdba0dd57dd47fab9d37a31074fe589694e8614 +size 2019627968 diff --git a/FunLLama3-8B.i1-IQ2_M.gguf b/FunLLama3-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..633bc5a --- /dev/null +++ b/FunLLama3-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c5d032cc43f55d10680045a2f8717bfaf590fff94bb505efd87e5be13452403 +size 2948281280 diff --git a/FunLLama3-8B.i1-IQ2_S.gguf b/FunLLama3-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..b48e816 --- /dev/null +++ b/FunLLama3-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cf495c252b0f6ad00f3a1b7ae79d117437821abe7cb687019245567978edfb +size 2758489024 diff --git a/FunLLama3-8B.i1-IQ2_XS.gguf b/FunLLama3-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0a4cc42 --- /dev/null +++ b/FunLLama3-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1a5618885a40e0cb820b138e70106fe37df5469d9a6192a874428393d596e6 +size 2605781952 diff --git a/FunLLama3-8B.i1-IQ2_XXS.gguf b/FunLLama3-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e62db79 --- /dev/null +++ b/FunLLama3-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6293c48bd22ab18a2b397c87843b8bd497b8b28fc5127d443ea02d1fe8e4342 +size 2399212480 diff --git a/FunLLama3-8B.i1-IQ3_M.gguf b/FunLLama3-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..d2fff6a --- /dev/null +++ b/FunLLama3-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504eb8305d8bbd11f913c42b10a01daf498181cca1a09007cd1ebc610374bf67 +size 3784823744 diff --git a/FunLLama3-8B.i1-IQ3_S.gguf b/FunLLama3-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..06ee5c1 --- /dev/null +++ b/FunLLama3-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4123b6c62fb632feac7c7c53468ea99101bfcc709c31a64fb953677b54d2270d +size 3682325440 diff --git a/FunLLama3-8B.i1-IQ3_XS.gguf b/FunLLama3-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..17ab141 --- /dev/null +++ b/FunLLama3-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d71b9087f48e6c95471755e09267767c4be514618084b5f3c1b8fe8ab771ad0 +size 3518747584 diff --git a/FunLLama3-8B.i1-IQ3_XXS.gguf b/FunLLama3-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..016bb55 --- /dev/null +++ b/FunLLama3-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59832520a3b597d414a15daa455b83c1ffb80cb405cbc5611855f800f569ce5d +size 3274912704 diff --git a/FunLLama3-8B.i1-IQ4_XS.gguf b/FunLLama3-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..14b01d3 --- /dev/null +++ b/FunLLama3-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d8c3216b550224e1b5fc24a7e5747efcc64d7c539fed9ebb1e8700a5793029 +size 4447663040 diff --git a/FunLLama3-8B.i1-Q2_K.gguf b/FunLLama3-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..487e0ca --- /dev/null +++ b/FunLLama3-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1570d7116a29610a2748f56fd334b0961b95a939f683e7ec42e0daf5351dc5 +size 3179131840 diff --git a/FunLLama3-8B.i1-Q3_K_L.gguf b/FunLLama3-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c15f0e2 --- /dev/null +++ b/FunLLama3-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e5d018893c7e95a351758e56f6a8f75baa31221b0f69cc95cf2ce192e56d99 +size 4321956800 diff --git a/FunLLama3-8B.i1-Q3_K_M.gguf b/FunLLama3-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a92cb41 --- /dev/null +++ b/FunLLama3-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6feba88f91ae4475ba0da9a5292cd7d59498739dabd346b8b8ead01087c0c0c5 +size 4018918336 diff --git a/FunLLama3-8B.i1-Q3_K_S.gguf b/FunLLama3-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..25db101 --- /dev/null +++ b/FunLLama3-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7245c99d791fc373c323518df97c9dcc0d435fc04070b8d3fb1a8915a7527491 +size 3664499648 diff --git a/FunLLama3-8B.i1-Q4_0.gguf b/FunLLama3-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..fe29939 --- /dev/null +++ b/FunLLama3-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f781436a55ad8aec323e85c50a4aab44e097ea73b07e4a20179e8833519ef9 +size 4675892160 diff --git a/FunLLama3-8B.i1-Q4_K_M.gguf b/FunLLama3-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a70d40a --- /dev/null +++ b/FunLLama3-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c794ac26b5e2aa13cc150489938047a9666d17b3ce44f1c042793a061227b0b4 +size 4920734656 diff --git a/FunLLama3-8B.i1-Q4_K_S.gguf b/FunLLama3-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..06264c8 --- /dev/null +++ b/FunLLama3-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87401f0c2d8d3f73c071ef92242424b4f26863f59770d2feeec18219b762a5f +size 4692669376 diff --git a/FunLLama3-8B.i1-Q5_K_M.gguf b/FunLLama3-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..23ae4a3 --- /dev/null +++ b/FunLLama3-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46dab5a0035ffa6e5dd1aa8568afb47924bd83c05116c88c7d1e0990aca860d5 +size 5732987840 diff --git a/FunLLama3-8B.i1-Q5_K_S.gguf b/FunLLama3-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..33092e8 --- /dev/null +++ b/FunLLama3-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80107ac61026c7b5e5300032bcd54550abe635b0646e1a277001318b009a4e3 +size 5599294400 diff --git a/FunLLama3-8B.i1-Q6_K.gguf b/FunLLama3-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..8cc24ba --- /dev/null +++ b/FunLLama3-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abcf081cbeb4ad7c8a973a87c94a03d5a22d2a8a311ba0ad98fa0fc803769a7 +size 6596006848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a25802c --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: bunnycore/FunLLama3-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/bunnycore/FunLLama3-8B + + +static quants are available at https://huggingface.co/mradermacher/FunLLama3-8B-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/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/FunLLama3-8B-i1-GGUF/resolve/main/FunLLama3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..3470b8c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eed52a0c17b19992176260f0dd07b19fb35d46178171da47fee8801843b78f7 +size 4988157