commit 73b02c8f626c4f6fdd9d30aac59c9960245efa73 Author: ModelHub XC Date: Thu Jun 11 14:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Yi-1.5-9B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e0f73e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Yi-1.5-9B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..82d4bf8 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: 01-ai/Yi-1.5-9B-Chat +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/01-ai/Yi-1.5-9B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-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/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.IQ3_XS.gguf) | IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.IQ3_M.gguf) | IQ3_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q5_K_S.gguf) | Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q5_K_M.gguf) | Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.Q8_0.gguf) | Q8_0 | 9.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-GGUF/resolve/main/Yi-1.5-9B-Chat.f16.gguf) | f16 | 17.8 | 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/Yi-1.5-9B-Chat.IQ3_M.gguf b/Yi-1.5-9B-Chat.IQ3_M.gguf new file mode 100644 index 0000000..660d884 --- /dev/null +++ b/Yi-1.5-9B-Chat.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f222c4e5982a54dfceaed5653d204c0f2c2100a542313ae24930a4f88013b15 +size 4055462592 diff --git a/Yi-1.5-9B-Chat.IQ3_S.gguf b/Yi-1.5-9B-Chat.IQ3_S.gguf new file mode 100644 index 0000000..0885ac7 --- /dev/null +++ b/Yi-1.5-9B-Chat.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6c3fd80ccc30e44e90b7ddb72762db05d78bd72cec8e3b1850c00cfdb1af90 +size 3912577728 diff --git a/Yi-1.5-9B-Chat.IQ3_XS.gguf b/Yi-1.5-9B-Chat.IQ3_XS.gguf new file mode 100644 index 0000000..7537622 --- /dev/null +++ b/Yi-1.5-9B-Chat.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4d296d7d8405ae4e9d695cd32b0e177a849860f7571694d966150d51c7f874 +size 3717935808 diff --git a/Yi-1.5-9B-Chat.IQ4_XS.gguf b/Yi-1.5-9B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..928feb9 --- /dev/null +++ b/Yi-1.5-9B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdeb37b491570cc8c978daf2e231275a5315b2bb25ae899753649450ccf3bbf +size 4827280064 diff --git a/Yi-1.5-9B-Chat.Q2_K.gguf b/Yi-1.5-9B-Chat.Q2_K.gguf new file mode 100644 index 0000000..33ae0fc --- /dev/null +++ b/Yi-1.5-9B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09befe8780a6bde69e5361d09480608dc4712a274d687d9c60ec11c5b573082 +size 3354325696 diff --git a/Yi-1.5-9B-Chat.Q3_K_L.gguf b/Yi-1.5-9B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..ac5dade --- /dev/null +++ b/Yi-1.5-9B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c47563293b40b7a3460b6f071d4a28bbca063a72b5b5bf8b10f86b115b97eeb +size 4690752192 diff --git a/Yi-1.5-9B-Chat.Q3_K_M.gguf b/Yi-1.5-9B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..26915d1 --- /dev/null +++ b/Yi-1.5-9B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184966e37986775213607dbe8263133d35ebb727e535a551ff5ede855543af8e +size 4324405952 diff --git a/Yi-1.5-9B-Chat.Q3_K_S.gguf b/Yi-1.5-9B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..13cd4f1 --- /dev/null +++ b/Yi-1.5-9B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c181d35f405dcde21fd71fdaf53aa20912980315033587e91e2df490c6e3cf +size 3899208384 diff --git a/Yi-1.5-9B-Chat.Q4_K_M.gguf b/Yi-1.5-9B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..5ba4733 --- /dev/null +++ b/Yi-1.5-9B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f01b8700781780fd82db119c81f30843c0a9ccd3be5dfe842c545af7cd4220 +size 5328958144 diff --git a/Yi-1.5-9B-Chat.Q4_K_S.gguf b/Yi-1.5-9B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..3cb2184 --- /dev/null +++ b/Yi-1.5-9B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84967016a8dcbb216908d7482a18301e4151365ecbbc56864550a71d9cb00cce +size 5071860416 diff --git a/Yi-1.5-9B-Chat.Q5_K_M.gguf b/Yi-1.5-9B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..9ae610c --- /dev/null +++ b/Yi-1.5-9B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd765892df8d8d931eb84aeda189ad5883b4b53b41c51706b95241254b1b6ee7 +size 6258258624 diff --git a/Yi-1.5-9B-Chat.Q5_K_S.gguf b/Yi-1.5-9B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..479a46e --- /dev/null +++ b/Yi-1.5-9B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f4a2c9d00be691aeb210e821d977c41a2f69699237d0de9e41d12da4430c0a +size 6107853504 diff --git a/Yi-1.5-9B-Chat.Q6_K.gguf b/Yi-1.5-9B-Chat.Q6_K.gguf new file mode 100644 index 0000000..0ee911c --- /dev/null +++ b/Yi-1.5-9B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a523a288f15b6341754fa2174cf1f86487c126d9c1e39dbcc4a897618cdd036 +size 7245640384 diff --git a/Yi-1.5-9B-Chat.Q8_0.gguf b/Yi-1.5-9B-Chat.Q8_0.gguf new file mode 100644 index 0000000..a40c2bd --- /dev/null +++ b/Yi-1.5-9B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8afe0ffffe55457ac8919305ce9e9aba56d4637854d75c8d705d42a9c8a5b8c +size 9383916224 diff --git a/Yi-1.5-9B-Chat.f16.gguf b/Yi-1.5-9B-Chat.f16.gguf new file mode 100644 index 0000000..ef20d65 --- /dev/null +++ b/Yi-1.5-9B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c390825330d93bea46eb3a9a7f98312d6230749ef9f704370d783ade2da5fe44 +size 17661113024