commit 97d3a63f1fa1f4b3f6c53d1a899e9d62f0a8d9ab Author: ModelHub XC Date: Mon Aug 17 23:33:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-KokoroChat-Low-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..491d305 --- /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-3.1-KokoroChat-Low.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Low.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-KokoroChat-Low.IQ4_XS.gguf b/Llama-3.1-KokoroChat-Low.IQ4_XS.gguf new file mode 100644 index 0000000..770b1be --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af9ec2d2ef9f5f057f1362bfd21974a8f5dc5b0ab6bed076f7c449eb454766b +size 4484364608 diff --git a/Llama-3.1-KokoroChat-Low.Q2_K.gguf b/Llama-3.1-KokoroChat-Low.Q2_K.gguf new file mode 100644 index 0000000..067ac17 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8566fbbf10c7635dd0c4d4baddad09198d43376f3a167da4ba64f79c8e05cc74 +size 3179133248 diff --git a/Llama-3.1-KokoroChat-Low.Q3_K_L.gguf b/Llama-3.1-KokoroChat-Low.Q3_K_L.gguf new file mode 100644 index 0000000..58154a7 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5af4bea6a8c12b740a2177fc8db385484eed911ff804c8f2300a013c09a250 +size 4321958208 diff --git a/Llama-3.1-KokoroChat-Low.Q3_K_M.gguf b/Llama-3.1-KokoroChat-Low.Q3_K_M.gguf new file mode 100644 index 0000000..dc13197 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38ad9f9b6081a2a4ac1b96de5b9e39bd3c37e4c50c6421e705e7bdb322057db +size 4018919744 diff --git a/Llama-3.1-KokoroChat-Low.Q3_K_S.gguf b/Llama-3.1-KokoroChat-Low.Q3_K_S.gguf new file mode 100644 index 0000000..324f8fd --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c631c36b3ae32a66f961a06d0d906ccb756c1f7e5acf18e42528b4f77b060e01 +size 3664501056 diff --git a/Llama-3.1-KokoroChat-Low.Q4_K_M.gguf b/Llama-3.1-KokoroChat-Low.Q4_K_M.gguf new file mode 100644 index 0000000..2dcf343 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9a0a2f978bddfada75c02432aafcb4542fe1e885f6b899b6150e332c7286b9 +size 4920736064 diff --git a/Llama-3.1-KokoroChat-Low.Q4_K_S.gguf b/Llama-3.1-KokoroChat-Low.Q4_K_S.gguf new file mode 100644 index 0000000..9fb9df9 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4f56316085fd4ab3f90a32b8b5c12a6d0f1154cc98f52b6c67dc129fa2ea6a +size 4692670784 diff --git a/Llama-3.1-KokoroChat-Low.Q5_K_M.gguf b/Llama-3.1-KokoroChat-Low.Q5_K_M.gguf new file mode 100644 index 0000000..96bd112 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af666e63614dd710e5e366c73a45a135ade8e819f705c5050f532cf4b27b5359 +size 5732989248 diff --git a/Llama-3.1-KokoroChat-Low.Q5_K_S.gguf b/Llama-3.1-KokoroChat-Low.Q5_K_S.gguf new file mode 100644 index 0000000..4ab7599 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fb73feec62cd9872dedee31e7a493d72367972258f9158742f8e29a312ceee +size 5599295808 diff --git a/Llama-3.1-KokoroChat-Low.Q6_K.gguf b/Llama-3.1-KokoroChat-Low.Q6_K.gguf new file mode 100644 index 0000000..6a74ad1 --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88bb2c0b4b6d61f263a0d4c5bb3a4ed93848087a34a1c1caf17abc4142fbeea3 +size 6596008256 diff --git a/Llama-3.1-KokoroChat-Low.Q8_0.gguf b/Llama-3.1-KokoroChat-Low.Q8_0.gguf new file mode 100644 index 0000000..4f2170f --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec67265e5437ca2b2be293d1697a73717562a2cbabebe0cd919e77ebe3466df +size 8540772672 diff --git a/Llama-3.1-KokoroChat-Low.f16.gguf b/Llama-3.1-KokoroChat-Low.f16.gguf new file mode 100644 index 0000000..08b06cc --- /dev/null +++ b/Llama-3.1-KokoroChat-Low.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5b0a3403b4b38236a30ead298ac22492e7e69db94707ed63bd049b7c97a6d2 +size 16068892992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6b611a --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: UEC-InabaLab/Llama-3.1-KokoroChat-Low +datasets: +- UEC-InabaLab/KokoroChat +language: +- ja +- en +library_name: transformers +license: +- llama3.1 +- gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- counseling +- dialogue-system +--- +## About + + + + + + + + + +static quants of https://huggingface.co/UEC-InabaLab/Llama-3.1-KokoroChat-Low + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-KokoroChat-Low-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-i1-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/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Low-GGUF/resolve/main/Llama-3.1-KokoroChat-Low.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. + +