commit e620341853ac251992a114e03831cfcb1dcfb821 Author: ModelHub XC Date: Sun Sep 27 14:27:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..038a472 --- /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 +Oppenheimer-Llama-3-MAAL-Ko-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Oppenheimer-Llama-3-MAAL-Ko-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_M.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_M.gguf new file mode 100644 index 0000000..eb0deae --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cb18b49f1e1b190a97efdb78d2215c3ac30c161cee482f60a46d7f3de82a75 +size 3784823104 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_S.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_S.gguf new file mode 100644 index 0000000..3c29618 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caef767f2a2c44b266bbed552f21927a6d3f8c2eee0275ffd6cb91e46950330b +size 3682324800 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_XS.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_XS.gguf new file mode 100644 index 0000000..6a9bc8c --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debd1b839a5dfa690b12e74a1c65a219ecf92e8880dca4d59a20179c47fd6419 +size 3518746944 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ4_XS.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ4_XS.gguf new file mode 100644 index 0000000..5b2eec7 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a624bb094afbf0fd2abf7d9700e7b75ef303414a039287a3256b0f31412c031 +size 4484362560 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q2_K.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q2_K.gguf new file mode 100644 index 0000000..cd6e307 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433ef8caa40e64e6558a4df75f517019d8a783b68826b7b2fd5fa72f2cf8375b +size 3179131200 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_L.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_L.gguf new file mode 100644 index 0000000..623d401 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cf7469678f7a94232e9623a278961ba23fb5cdb0a75a6f456576ed5fb372f9 +size 4321956160 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_M.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_M.gguf new file mode 100644 index 0000000..806f8fe --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097e49ea31745764236f3ed1fab3cdb1d8497cfe969808f37ec4994262c74902 +size 4018917696 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_S.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_S.gguf new file mode 100644 index 0000000..cc90685 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963a0a4067830a3f87680d9982a25edbed2099229f4fc7cd74857e6b1821a308 +size 3664499008 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_M.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_M.gguf new file mode 100644 index 0000000..9d1c89a --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac0359647dedbcaeb30be1fcc7390fab1a7240756868eaa63f69808803c1e2a +size 4920734016 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_S.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_S.gguf new file mode 100644 index 0000000..b945e75 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6651a17692916731b34a46eee734d730c288b718086653aaab705c86e0d3f642 +size 4692668736 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_M.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_M.gguf new file mode 100644 index 0000000..985bbab --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1b9668047f7ed0e99d096486473bfae628ec6ea255050e03a139d9fd96080f +size 5732987200 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_S.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_S.gguf new file mode 100644 index 0000000..0f30517 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f24fe864497628ccf447bf0ec222f44a4bc61daa83c0ed5e8bfc44986d1acbb +size 5599293760 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q6_K.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q6_K.gguf new file mode 100644 index 0000000..ea5a9c9 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11597e78dcf287380d71234128270bebdc5e2df6b71383a16412c7a3bc040e79 +size 6596006208 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.Q8_0.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q8_0.gguf new file mode 100644 index 0000000..656e685 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0421eb3e7e0b831decd5395f9a1bfee98b5becfd077bb88a9f4b2ecd100ece39 +size 8540770624 diff --git a/Oppenheimer-Llama-3-MAAL-Ko-8B.f16.gguf b/Oppenheimer-Llama-3-MAAL-Ko-8B.f16.gguf new file mode 100644 index 0000000..e3592a0 --- /dev/null +++ b/Oppenheimer-Llama-3-MAAL-Ko-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ba7768f4c517881e175c2c8a50f1dc4f95880f50db650c0d61661d02336a64 +size 16068890944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b232716 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: asiansoul/AIA-Llama-3-MAAL-Ko-8B-32k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + +static quants of https://huggingface.co/asiansoul/AIA-Llama-3-MAAL-Ko-8B-32k + + +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/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Oppenheimer-Llama-3-MAAL-Ko-8B-GGUF/resolve/main/Oppenheimer-Llama-3-MAAL-Ko-8B.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. + +