commit ef55c0d620c9ae7b4d86c19cd5641037202083f0 Author: ModelHub XC Date: Tue Jul 21 10:14:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/greesychat-turbo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35587fe --- /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 +greesychat-turbo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.f16.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +greesychat-turbo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4fb5728 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: OnlyCheeini/greesychat-turbo +datasets: +- OnlyCheeini/greesychat +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/OnlyCheeini/greesychat-turbo + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/greesychat-turbo-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/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/greesychat-turbo-GGUF/resolve/main/greesychat-turbo.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/greesychat-turbo.IQ4_XS.gguf b/greesychat-turbo.IQ4_XS.gguf new file mode 100644 index 0000000..a2b4257 --- /dev/null +++ b/greesychat-turbo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8fc411d5a2a93143d9160ab13f39d6a67d6adc86118944aa3d55c2504fa8619 +size 4484364768 diff --git a/greesychat-turbo.Q2_K.gguf b/greesychat-turbo.Q2_K.gguf new file mode 100644 index 0000000..6806066 --- /dev/null +++ b/greesychat-turbo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ad1fa92e965e6012078374d37306f5de8a6dba6e67e6397f636081c728c580 +size 3179133408 diff --git a/greesychat-turbo.Q3_K_L.gguf b/greesychat-turbo.Q3_K_L.gguf new file mode 100644 index 0000000..57b189a --- /dev/null +++ b/greesychat-turbo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed31b001eded942449878d4bf8bfbc0edb61272e9022e5fda7892103b5dedb13 +size 4321958368 diff --git a/greesychat-turbo.Q3_K_M.gguf b/greesychat-turbo.Q3_K_M.gguf new file mode 100644 index 0000000..8bdb7c6 --- /dev/null +++ b/greesychat-turbo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed568ccb1231c0aa262a7802a03f3ac55c6caa869d7fbecb057747c1f1b0983 +size 4018919904 diff --git a/greesychat-turbo.Q3_K_S.gguf b/greesychat-turbo.Q3_K_S.gguf new file mode 100644 index 0000000..70729d0 --- /dev/null +++ b/greesychat-turbo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bbb1f51a8a3da01e3696db35f88041aba6d7b9f2c0380e9ad815576e95a7efe +size 3664501216 diff --git a/greesychat-turbo.Q4_K_M.gguf b/greesychat-turbo.Q4_K_M.gguf new file mode 100644 index 0000000..4ea1d51 --- /dev/null +++ b/greesychat-turbo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179658731be3a336ef13f108a4c48849485fc697af35e7287282ba028d1833f9 +size 4920736224 diff --git a/greesychat-turbo.Q4_K_S.gguf b/greesychat-turbo.Q4_K_S.gguf new file mode 100644 index 0000000..7e367c1 --- /dev/null +++ b/greesychat-turbo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d0803981ebe6111d82809d3ea5deac8ab1ce2ae66697493efe706a26d1c79e +size 4692670944 diff --git a/greesychat-turbo.Q5_K_M.gguf b/greesychat-turbo.Q5_K_M.gguf new file mode 100644 index 0000000..d0eda54 --- /dev/null +++ b/greesychat-turbo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef468489f3b4fcc3d900b6eaec190fe044bb052eb48dd924f2bed2bf5633ea9 +size 5732989408 diff --git a/greesychat-turbo.Q5_K_S.gguf b/greesychat-turbo.Q5_K_S.gguf new file mode 100644 index 0000000..18b0641 --- /dev/null +++ b/greesychat-turbo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b8aca3b1d16fda76586759cbcb21565afd1d2034a310cf37eb6f0f76527c82 +size 5599295968 diff --git a/greesychat-turbo.Q6_K.gguf b/greesychat-turbo.Q6_K.gguf new file mode 100644 index 0000000..42a36ca --- /dev/null +++ b/greesychat-turbo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5013932f749fb89ed3dcff7c40e0fbee0a254bca781befad1f066c66b897323e +size 6596008416 diff --git a/greesychat-turbo.Q8_0.gguf b/greesychat-turbo.Q8_0.gguf new file mode 100644 index 0000000..3a72c8c --- /dev/null +++ b/greesychat-turbo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad9f0eb183a09b72835816022784680433ceec784ef1d7e5434e2ddbab8ccf7 +size 8540772832 diff --git a/greesychat-turbo.f16.gguf b/greesychat-turbo.f16.gguf new file mode 100644 index 0000000..6153440 --- /dev/null +++ b/greesychat-turbo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da46341268eb50cb1cd0a70caf0867b36f2eba88ade5ee30c9c1555b28590d4c +size 16068893152