commit f9a22624a7bf05261ec20a0531bc7d1100598a95 Author: ModelHub XC Date: Sat Jun 13 03:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/care-japanese-llama3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f22c8c6 --- /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 +care-japanese-llama3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +care-japanese-llama3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3e807f4 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: geyang627/care-japanese-llama3.1-8b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/geyang627/care-japanese-llama3.1-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#care-japanese-llama3.1-8b-GGUF).*** + +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/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/care-japanese-llama3.1-8b-GGUF/resolve/main/care-japanese-llama3.1-8b.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. + + diff --git a/care-japanese-llama3.1-8b.IQ4_XS.gguf b/care-japanese-llama3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..8aeadb0 --- /dev/null +++ b/care-japanese-llama3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1823c18dea0ee16252addafed40cd3b078847eb445d53acd3da88bfdd099c500 +size 4484363648 diff --git a/care-japanese-llama3.1-8b.Q2_K.gguf b/care-japanese-llama3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..12774a6 --- /dev/null +++ b/care-japanese-llama3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024ddd381e4114e676c38ee904052b6fdafc4942af058077de19e941a0dc118c +size 3179132288 diff --git a/care-japanese-llama3.1-8b.Q3_K_L.gguf b/care-japanese-llama3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..dd3037f --- /dev/null +++ b/care-japanese-llama3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1d02dd557bf82e5b58ac9f3325d5700338b906d2abea0e84d18af972f84053 +size 4321957248 diff --git a/care-japanese-llama3.1-8b.Q3_K_M.gguf b/care-japanese-llama3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..18e72c2 --- /dev/null +++ b/care-japanese-llama3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79ac7b3f9394aec05ffbefbac570687e83f2e92638ae0b00cddfdc201b71097 +size 4018918784 diff --git a/care-japanese-llama3.1-8b.Q3_K_S.gguf b/care-japanese-llama3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..a67089c --- /dev/null +++ b/care-japanese-llama3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07928b281ce86a8f0fca7b6b58c97235affdb19345f3278d852b4fc3709c220 +size 3664500096 diff --git a/care-japanese-llama3.1-8b.Q4_K_M.gguf b/care-japanese-llama3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..385edf6 --- /dev/null +++ b/care-japanese-llama3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c783dd32ee0cc2689ea7b3f6d9950451cd94da847eb8c2f31ba07f7dc712049 +size 4920735104 diff --git a/care-japanese-llama3.1-8b.Q4_K_S.gguf b/care-japanese-llama3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..19a79ec --- /dev/null +++ b/care-japanese-llama3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3788fdac964193667e0dc3da3429614c308552d687a415b460be193150d22b15 +size 4692669824 diff --git a/care-japanese-llama3.1-8b.Q5_K_M.gguf b/care-japanese-llama3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..aba9e9f --- /dev/null +++ b/care-japanese-llama3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab01ee00e5a7271055cb516b8ee859b0e6709cf6ea6e8b0a4fd62327c73f3f4 +size 5732988288 diff --git a/care-japanese-llama3.1-8b.Q5_K_S.gguf b/care-japanese-llama3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..b796265 --- /dev/null +++ b/care-japanese-llama3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dfe5b393764914279eb596297f8431b7df506b5a464891770f48bf5ff1c35d +size 5599294848 diff --git a/care-japanese-llama3.1-8b.Q6_K.gguf b/care-japanese-llama3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..d98f410 --- /dev/null +++ b/care-japanese-llama3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd7a4ca9fc70a0430ffb5e46cbbf3150145cb3f5edc80c06432111c5cf573c57 +size 6596007296 diff --git a/care-japanese-llama3.1-8b.Q8_0.gguf b/care-japanese-llama3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..83882cc --- /dev/null +++ b/care-japanese-llama3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370e9e9bf79f8ec4092fcdda9c454bda7de715410430403ae7f658bf5c3bc24a +size 8540771712 diff --git a/care-japanese-llama3.1-8b.f16.gguf b/care-japanese-llama3.1-8b.f16.gguf new file mode 100644 index 0000000..b335071 --- /dev/null +++ b/care-japanese-llama3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895630718622487fed70074e6ab15cd5174a3fbbe88b0888019604a37210d56f +size 16068892032