commit 95c5cc0b69a749e60a2491ebaa2618aa9cc0242c Author: ModelHub XC Date: Sun Jun 14 21:28:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Final-Llama-IoI-1L-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ec60177 --- /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 +Final-Llama-IoI-1L.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.f16.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-IoI-1L.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Final-Llama-IoI-1L.IQ4_XS.gguf b/Final-Llama-IoI-1L.IQ4_XS.gguf new file mode 100644 index 0000000..370c068 --- /dev/null +++ b/Final-Llama-IoI-1L.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5fae09cac50a0e19d2e804c516276d8691cd203cd76c9f0d8dd2e58922e299 +size 4484367776 diff --git a/Final-Llama-IoI-1L.Q2_K.gguf b/Final-Llama-IoI-1L.Q2_K.gguf new file mode 100644 index 0000000..a9aadd6 --- /dev/null +++ b/Final-Llama-IoI-1L.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf74c8e252d539b94ec9c2d490619e87c50094a6ce0ae3fd29035d723781240 +size 3179136416 diff --git a/Final-Llama-IoI-1L.Q3_K_L.gguf b/Final-Llama-IoI-1L.Q3_K_L.gguf new file mode 100644 index 0000000..6447ea9 --- /dev/null +++ b/Final-Llama-IoI-1L.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d36cbbb84bb2032e19c3726bd45a2c4deced3c189b491fb9bcad5647e8c587 +size 4321961376 diff --git a/Final-Llama-IoI-1L.Q3_K_M.gguf b/Final-Llama-IoI-1L.Q3_K_M.gguf new file mode 100644 index 0000000..18f665f --- /dev/null +++ b/Final-Llama-IoI-1L.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3e32fc26d6158d84ba418a021ba45c927dc957611f0f7826b26e428ed733f3 +size 4018922912 diff --git a/Final-Llama-IoI-1L.Q3_K_S.gguf b/Final-Llama-IoI-1L.Q3_K_S.gguf new file mode 100644 index 0000000..9ed3bbb --- /dev/null +++ b/Final-Llama-IoI-1L.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355a8925df0bb9d537ff1b70b79924f63f30faa17599401857f3d26ace18d324 +size 3664504224 diff --git a/Final-Llama-IoI-1L.Q4_K_M.gguf b/Final-Llama-IoI-1L.Q4_K_M.gguf new file mode 100644 index 0000000..7a98a33 --- /dev/null +++ b/Final-Llama-IoI-1L.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ff21eba56a20e1643059f6265d76cf1d83a9634cb3c828845eba5927df5f16 +size 4920739232 diff --git a/Final-Llama-IoI-1L.Q4_K_S.gguf b/Final-Llama-IoI-1L.Q4_K_S.gguf new file mode 100644 index 0000000..83a8b01 --- /dev/null +++ b/Final-Llama-IoI-1L.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb1b2eed20629466fd9224a7e316af16244e7e34c8c2995f3e43e7620ede4c12 +size 4692673952 diff --git a/Final-Llama-IoI-1L.Q5_K_M.gguf b/Final-Llama-IoI-1L.Q5_K_M.gguf new file mode 100644 index 0000000..c27d995 --- /dev/null +++ b/Final-Llama-IoI-1L.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6138bde7cf22e58b592246400279291e856586ae9e837e8e4e01aaba14bf42c +size 5732992416 diff --git a/Final-Llama-IoI-1L.Q5_K_S.gguf b/Final-Llama-IoI-1L.Q5_K_S.gguf new file mode 100644 index 0000000..7f287c4 --- /dev/null +++ b/Final-Llama-IoI-1L.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c99a27cc96964222a769a9a4d875f4bbab7d71be0e389bd882ec26448f552b5 +size 5599298976 diff --git a/Final-Llama-IoI-1L.Q6_K.gguf b/Final-Llama-IoI-1L.Q6_K.gguf new file mode 100644 index 0000000..d68b462 --- /dev/null +++ b/Final-Llama-IoI-1L.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414612d749f80bc8917afd9cadd95588945fe72d6be4bb005ddaeec8d51cb2e8 +size 6596011424 diff --git a/Final-Llama-IoI-1L.Q8_0.gguf b/Final-Llama-IoI-1L.Q8_0.gguf new file mode 100644 index 0000000..2db05c6 --- /dev/null +++ b/Final-Llama-IoI-1L.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d3fea44590e44279742936bf1e8e1de33875dcdfd3494c1b49065fa46f8694 +size 8540775840 diff --git a/Final-Llama-IoI-1L.f16.gguf b/Final-Llama-IoI-1L.f16.gguf new file mode 100644 index 0000000..3c2a910 --- /dev/null +++ b/Final-Llama-IoI-1L.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da49069d005d339d1843eac89631a3652706aa4b68b1635943978ede533fda11 +size 16068896160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..60bca3b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: psyonp/Final-Llama-IoI-1L +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/psyonp/Final-Llama-IoI-1L + + +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/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-IoI-1L-GGUF/resolve/main/Final-Llama-IoI-1L.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. + +