commit 2e645a59883de6796959cabfdd4aa13312207d75 Author: ModelHub XC Date: Wed Apr 22 09:53:48 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Yi-1.5-9B-Chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6919b21 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..56fd0ae --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: 01-ai/Yi-1.5-9B-Chat +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +weighted/imatrix quants of https://huggingface.co/01-ai/Yi-1.5-9B-Chat + + +static quants are available at https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-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-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 3.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 5.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-i1-GGUF/resolve/main/Yi-1.5-9B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 7.3 | practically like static Q6_K | + +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.i1-IQ1_M.gguf b/Yi-1.5-9B-Chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..a47cfac --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca18f3a648637c45974c7238541d247ff8aeabdb455c666f53d348a868e1833 +size 2181641120 diff --git a/Yi-1.5-9B-Chat.i1-IQ1_S.gguf b/Yi-1.5-9B-Chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..a50dd70 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:898d128300fe13ce9bf1980b78fa1bbda90b4a8c26549c067d1f48751c07a6e2 +size 2014573472 diff --git a/Yi-1.5-9B-Chat.i1-IQ2_M.gguf b/Yi-1.5-9B-Chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..c8dec4e --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8a8f038fc7010e4fcdcc030401d56b59c2c06d7604cb91d10213a2302684f4 +size 3098112928 diff --git a/Yi-1.5-9B-Chat.i1-IQ2_S.gguf b/Yi-1.5-9B-Chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..e37a127 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ac03b00b84bab3ae917388768c2df45bb94e33a286d29afa1ae36b2ce856a8 +size 2875356064 diff --git a/Yi-1.5-9B-Chat.i1-IQ2_XS.gguf b/Yi-1.5-9B-Chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fc02d15 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9280a3ef497eed323cfd79900786c6bc7f3171f3939bab83a13f0aed8c72e31b +size 2708009888 diff --git a/Yi-1.5-9B-Chat.i1-IQ2_XXS.gguf b/Yi-1.5-9B-Chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..77eded1 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfce468e2bea3af1235d840a8775e4cbeb16aeb6f5fbb90cd16bc9a94a8e74bf +size 2460087200 diff --git a/Yi-1.5-9B-Chat.i1-IQ3_M.gguf b/Yi-1.5-9B-Chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..e2732f7 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3499bc1c931850f7344c568bec03c0caf5c7fe61b641673e6f39e730b7e1c1e +size 4055462816 diff --git a/Yi-1.5-9B-Chat.i1-IQ3_S.gguf b/Yi-1.5-9B-Chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..4364147 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c852c1965899bcdca11dd82a30bb8fb7afd65b7cc2ef19e12c252fa9eb31cd +size 3912577952 diff --git a/Yi-1.5-9B-Chat.i1-IQ3_XS.gguf b/Yi-1.5-9B-Chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0d8a5bb --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dddc40312d623faf85d37128679629de11fa444083f0102c7341f4b673421c4 +size 3717936032 diff --git a/Yi-1.5-9B-Chat.i1-IQ3_XXS.gguf b/Yi-1.5-9B-Chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..57d014a --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b81553b01eed3eb69d229f60bd3af809770a68e1875be0678d526a728a098e +size 3474322336 diff --git a/Yi-1.5-9B-Chat.i1-IQ4_XS.gguf b/Yi-1.5-9B-Chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..75e1583 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924195eb0e1322d9821a88659541dc8d51f1c5e90e09ef95845caa48df497f96 +size 4785009568 diff --git a/Yi-1.5-9B-Chat.i1-Q2_K.gguf b/Yi-1.5-9B-Chat.i1-Q2_K.gguf new file mode 100644 index 0000000..609575e --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ddf7d97344dc4c1aef4f8c2269b60dd00d6a0aca09bbfdf01136bdcd0338ed7 +size 3354325920 diff --git a/Yi-1.5-9B-Chat.i1-Q2_K_S.gguf b/Yi-1.5-9B-Chat.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9b10b12 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8d93baa153f7cd6ba7e020d486f903e4e244033c02b83343948c90a5e094ef +size 3116135648 diff --git a/Yi-1.5-9B-Chat.i1-Q3_K_L.gguf b/Yi-1.5-9B-Chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8cea483 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a22b908a350329a88797742c3764c013a7ddc6fda6bf6daebda9be9029c3552 +size 4690752416 diff --git a/Yi-1.5-9B-Chat.i1-Q3_K_M.gguf b/Yi-1.5-9B-Chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1fb4aeb --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c193eead4114c75f44066d3a4260e8bfdf107d547a7d6b66db48b3ad18463467 +size 4324406176 diff --git a/Yi-1.5-9B-Chat.i1-Q3_K_S.gguf b/Yi-1.5-9B-Chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d843d7b --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf96042976b5f8308a9d9fdca0f4174a39691ac0e92f92fd7ad2293db1a3ecd +size 3899208608 diff --git a/Yi-1.5-9B-Chat.i1-Q4_0.gguf b/Yi-1.5-9B-Chat.i1-Q4_0.gguf new file mode 100644 index 0000000..b916345 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315da3964f67b066ace66a11da53ce750b7cca8020f0c41175ce7c970467ac05 +size 5053903776 diff --git a/Yi-1.5-9B-Chat.i1-Q4_K_M.gguf b/Yi-1.5-9B-Chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4d8764d --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66be9765553b7bff319894cffd9daf4b70656815bd17dfa8e500f4b88529a378 +size 5328958368 diff --git a/Yi-1.5-9B-Chat.i1-Q4_K_S.gguf b/Yi-1.5-9B-Chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..26768c6 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcf5221cfe1b2920eeac378d4a5719715b1305e332ad6ef69546ee12902db91 +size 5071860640 diff --git a/Yi-1.5-9B-Chat.i1-Q5_K_M.gguf b/Yi-1.5-9B-Chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a0efd3b --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5061c51dfc61a52f950a22049a29694ece68ff0d681e5fcfac830fb7a951f2fe +size 6258258848 diff --git a/Yi-1.5-9B-Chat.i1-Q5_K_S.gguf b/Yi-1.5-9B-Chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..33dfdc0 --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347338b7947ff5cb2ff44ac64c02033d41d8be14027ffd95e56eb73fcd800310 +size 6107853728 diff --git a/Yi-1.5-9B-Chat.i1-Q6_K.gguf b/Yi-1.5-9B-Chat.i1-Q6_K.gguf new file mode 100644 index 0000000..fe149ae --- /dev/null +++ b/Yi-1.5-9B-Chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ce66dec3014bea061db999ebe814db64cb181657395d3ebf6e173991e95888 +size 7245640608 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..7cd0ef2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5249b66c9d4bbc80a1ad0e9ba42634dd71a4ec91545bd547e7b2ae9e8d808c11 +size 6843279