commit 22474ab346f08b6237990db71fa8e8c41be99a65 Author: ModelHub XC Date: Tue May 26 09:59:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-KokoroChat-Full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6195f60 --- /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-Full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KokoroChat-Full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-KokoroChat-Full.IQ4_XS.gguf b/Llama-3.1-KokoroChat-Full.IQ4_XS.gguf new file mode 100644 index 0000000..d72d4ae --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975a31caa56f93c86cd50e22a54586a3913980b020a2d88aebf902431ae1afe2 +size 4484364608 diff --git a/Llama-3.1-KokoroChat-Full.Q2_K.gguf b/Llama-3.1-KokoroChat-Full.Q2_K.gguf new file mode 100644 index 0000000..32a8d3e --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175b35d7cdaf041a5e0982ff157b4d3cfd22720e901d53b87e2be7e17349208e +size 3179133248 diff --git a/Llama-3.1-KokoroChat-Full.Q3_K_L.gguf b/Llama-3.1-KokoroChat-Full.Q3_K_L.gguf new file mode 100644 index 0000000..350fee8 --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f226562109bfc5eddb3cd5fb5240c731a0d8e6c43138992c6e0247d6e123f96 +size 4321958208 diff --git a/Llama-3.1-KokoroChat-Full.Q3_K_M.gguf b/Llama-3.1-KokoroChat-Full.Q3_K_M.gguf new file mode 100644 index 0000000..9be9c33 --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad9e2fbe6505c12f2dedb8733e52bfcb0c361cf3783eb2f4e2e49982522834 +size 4018919744 diff --git a/Llama-3.1-KokoroChat-Full.Q3_K_S.gguf b/Llama-3.1-KokoroChat-Full.Q3_K_S.gguf new file mode 100644 index 0000000..bda6ce0 --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ca9b953045e3815a7c52eacdab8e03fa50a8fc53b1c08c07c387d0cd742c08 +size 3664501056 diff --git a/Llama-3.1-KokoroChat-Full.Q4_K_M.gguf b/Llama-3.1-KokoroChat-Full.Q4_K_M.gguf new file mode 100644 index 0000000..a6a550a --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59dfe73c79223e6eb1fe00ce7e2fc7af5c57023aa23f404436fe3580445de1ea +size 4920736064 diff --git a/Llama-3.1-KokoroChat-Full.Q4_K_S.gguf b/Llama-3.1-KokoroChat-Full.Q4_K_S.gguf new file mode 100644 index 0000000..7a86c47 --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5af1adc06e6d1698b9143882249cc74e753573017cfa21531dd2f595eec92d0 +size 4692670784 diff --git a/Llama-3.1-KokoroChat-Full.Q5_K_M.gguf b/Llama-3.1-KokoroChat-Full.Q5_K_M.gguf new file mode 100644 index 0000000..f2b4d80 --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d11bef724d989178e388e21582cb1b9da408bd5c7888a9cfb812f828738aea +size 5732989248 diff --git a/Llama-3.1-KokoroChat-Full.Q5_K_S.gguf b/Llama-3.1-KokoroChat-Full.Q5_K_S.gguf new file mode 100644 index 0000000..eb1095a --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de961f622ee43862f0122910154eedfd37ee933e735bd28201523d15b6fae0df +size 5599295808 diff --git a/Llama-3.1-KokoroChat-Full.Q6_K.gguf b/Llama-3.1-KokoroChat-Full.Q6_K.gguf new file mode 100644 index 0000000..d4266a6 --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd053391192f6c060db3d9864a049b7460c67f59f3edf08060c8dc398ac2a9d +size 6596008256 diff --git a/Llama-3.1-KokoroChat-Full.Q8_0.gguf b/Llama-3.1-KokoroChat-Full.Q8_0.gguf new file mode 100644 index 0000000..ea1dc4a --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:674d5557eecce7a90ee6b28b0ee4ea10ec592162e4195fe792ef2b39ab40b554 +size 8540772672 diff --git a/Llama-3.1-KokoroChat-Full.f16.gguf b/Llama-3.1-KokoroChat-Full.f16.gguf new file mode 100644 index 0000000..db4d40b --- /dev/null +++ b/Llama-3.1-KokoroChat-Full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7a99ab932f658f6603cb77e5f10c80b0613d8c67ae5902123491010b3d9a88 +size 16068892992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..684e330 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: UEC-InabaLab/Llama-3.1-KokoroChat-Full +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-Full + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-KokoroChat-Full-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-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-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KokoroChat-Full-GGUF/resolve/main/Llama-3.1-KokoroChat-Full.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. + +