commit a16e4f13e22f5072abebe2874e25fbc2df73cbbe Author: ModelHub XC Date: Tue Oct 6 15:45:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e099c83 --- /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 +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-ELYZA-JP-8B-ojousama-chosen.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.IQ4_XS.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.IQ4_XS.gguf new file mode 100644 index 0000000..acc5dba --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400aeaa693aa8dafff1ac5e5e0e4e7f4f36648be642a287411494ced04ad7b18 +size 4484363360 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q2_K.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q2_K.gguf new file mode 100644 index 0000000..85f15cd --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b406eae9f5c561fb3973ac93631a083373a6804edd60cf487aa00c80cffa90a +size 3179132000 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_L.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_L.gguf new file mode 100644 index 0000000..c7939f3 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c18bb59dfbe5041c852d3e496e11e348d3e14606c4ca861b4866319ccd24d1 +size 4321956960 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_M.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_M.gguf new file mode 100644 index 0000000..ff6de58 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63142e5ff28fc000c6f406b502c698137ce5b8b07fd35e9efd2f8245e9eb738a +size 4018918496 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_S.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_S.gguf new file mode 100644 index 0000000..b133e57 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac594e91dce54188b4fd42e1151daf015dd30bea051a39cf4f558cb1b65da1f +size 3664499808 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_M.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_M.gguf new file mode 100644 index 0000000..3a69e23 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7c1b56766e4fae245493f4bcedadf0b3d8d2b5144ef9d92e9442e173860d94c +size 4920734816 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_S.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_S.gguf new file mode 100644 index 0000000..df9ae96 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e4703115cfa00f6654887fae24de8dcadb398d6152d4fbbaee8709f0611336 +size 4692669536 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_M.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_M.gguf new file mode 100644 index 0000000..521b081 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73af7118331ac0ef6caadd26a1db15381f51b8803c6fcfbd830831047b48a47 +size 5732988000 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_S.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_S.gguf new file mode 100644 index 0000000..e4c02e8 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7dafb7af0c6d608c661c98548840fbcc9376ae6bc88ad88c4286ee453b9b6ce +size 5599294560 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q6_K.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q6_K.gguf new file mode 100644 index 0000000..e543ed3 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6d4761e79ef7bb613b6c46ae6c69580cdfc43c95c6f187b46686c430e0d6b7 +size 6596007008 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q8_0.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q8_0.gguf new file mode 100644 index 0000000..7b67753 --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e239062cca467e9dd45257f7e6043d33cfa18cf62fda20b6989c85895373cf13 +size 8540771424 diff --git a/Llama-3-ELYZA-JP-8B-ojousama-chosen.f16.gguf b/Llama-3-ELYZA-JP-8B-ojousama-chosen.f16.gguf new file mode 100644 index 0000000..9f84abb --- /dev/null +++ b/Llama-3-ELYZA-JP-8B-ojousama-chosen.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059f41da9e965ed9a37960f8a7040d37a25c1abed012acf639fb53397d52d33a +size 16068891744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..62b048c --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Nisk36/Llama-3-ELYZA-JP-8B-ojousama-chosen +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Nisk36/Llama-3-ELYZA-JP-8B-ojousama-chosen + + +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/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-ELYZA-JP-8B-ojousama-chosen-GGUF/resolve/main/Llama-3-ELYZA-JP-8B-ojousama-chosen.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. + +