commit 43895d307e23e31502c2740abe8ad6aa70474dac Author: ModelHub XC Date: Thu Jun 11 14:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Yi-1.5-9B-Chat-16K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49bf902 --- /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-16K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-16K.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bce787c --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: 01-ai/Yi-1.5-9B-Chat-16K +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-16K + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-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-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.IQ3_XS.gguf) | IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.IQ3_M.gguf) | IQ3_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q5_K_S.gguf) | Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q5_K_M.gguf) | Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.Q8_0.gguf) | Q8_0 | 9.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-Chat-16K-GGUF/resolve/main/Yi-1.5-9B-Chat-16K.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-16K.IQ3_M.gguf b/Yi-1.5-9B-Chat-16K.IQ3_M.gguf new file mode 100644 index 0000000..a2f6808 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42ecb76e5b911392edf6ffe113272494ec5494f9608a68a5d621298341333967 +size 4055462688 diff --git a/Yi-1.5-9B-Chat-16K.IQ3_S.gguf b/Yi-1.5-9B-Chat-16K.IQ3_S.gguf new file mode 100644 index 0000000..017fcc4 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0321748b4cd14f8a5752f96dba2492798c100329c08dcc2f8ca3507f8253bcd +size 3912577824 diff --git a/Yi-1.5-9B-Chat-16K.IQ3_XS.gguf b/Yi-1.5-9B-Chat-16K.IQ3_XS.gguf new file mode 100644 index 0000000..eae6d4a --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7fc0e31a97d4ed78918106852521617ee918553fb56c0ff05d913545c7a959 +size 3717935904 diff --git a/Yi-1.5-9B-Chat-16K.IQ4_XS.gguf b/Yi-1.5-9B-Chat-16K.IQ4_XS.gguf new file mode 100644 index 0000000..34356f8 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25de1ffdccbb046e7f1f175d31d3980fbb002d9eb1095615cc1296c38aca05c6 +size 4827280160 diff --git a/Yi-1.5-9B-Chat-16K.Q2_K.gguf b/Yi-1.5-9B-Chat-16K.Q2_K.gguf new file mode 100644 index 0000000..c5244c6 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f138fa543a35f503dbfb9393ac5e9ed93c51e035feb75b9c260fd351388bf585 +size 3354325792 diff --git a/Yi-1.5-9B-Chat-16K.Q3_K_L.gguf b/Yi-1.5-9B-Chat-16K.Q3_K_L.gguf new file mode 100644 index 0000000..b9f6715 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6589e7dd8e2266fe8ce382497edbcb6ded211d967c77839555cae94330b8c82f +size 4690752288 diff --git a/Yi-1.5-9B-Chat-16K.Q3_K_M.gguf b/Yi-1.5-9B-Chat-16K.Q3_K_M.gguf new file mode 100644 index 0000000..0082a51 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611dd592614e9933ebbd07a278023003f3c0bd54f2f85671b953c20e5f0f525d +size 4324406048 diff --git a/Yi-1.5-9B-Chat-16K.Q3_K_S.gguf b/Yi-1.5-9B-Chat-16K.Q3_K_S.gguf new file mode 100644 index 0000000..2cb3689 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f42fef416a0f22939fa1859f037d9112600cdfc4204125e32223bd82be93c5 +size 3899208480 diff --git a/Yi-1.5-9B-Chat-16K.Q4_K_M.gguf b/Yi-1.5-9B-Chat-16K.Q4_K_M.gguf new file mode 100644 index 0000000..79f127c --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb8e673c81ab728342f70f6f844e920e30d7b50869ad7af475fa97ae528be6c4 +size 5328958240 diff --git a/Yi-1.5-9B-Chat-16K.Q4_K_S.gguf b/Yi-1.5-9B-Chat-16K.Q4_K_S.gguf new file mode 100644 index 0000000..7fa92d6 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2458d7e9ae609e9bebc1f3790325a36a389db1faba977afe57540cdfb36b3aab +size 5071860512 diff --git a/Yi-1.5-9B-Chat-16K.Q5_K_M.gguf b/Yi-1.5-9B-Chat-16K.Q5_K_M.gguf new file mode 100644 index 0000000..9f66fee --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43559bdef7102f003b1ba3aa2f4ce806211bdc9530055f35ff0e86f1f839e68b +size 6258258720 diff --git a/Yi-1.5-9B-Chat-16K.Q5_K_S.gguf b/Yi-1.5-9B-Chat-16K.Q5_K_S.gguf new file mode 100644 index 0000000..178618a --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718f2724939944fe5c22b4f5448ffbf59f7ff4bb6c374cadd5d0258f15d905b6 +size 6107853600 diff --git a/Yi-1.5-9B-Chat-16K.Q6_K.gguf b/Yi-1.5-9B-Chat-16K.Q6_K.gguf new file mode 100644 index 0000000..c7e52a0 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63a082ba09890ff2be796ae9773bbf22b4f51786f501bbdd5db05b9739714074 +size 7245640480 diff --git a/Yi-1.5-9B-Chat-16K.Q8_0.gguf b/Yi-1.5-9B-Chat-16K.Q8_0.gguf new file mode 100644 index 0000000..d6bd5d1 --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2117553df5768bef5781bc8c03925afd005129f20f20ee3bad972d9eb5884452 +size 9383916320 diff --git a/Yi-1.5-9B-Chat-16K.f16.gguf b/Yi-1.5-9B-Chat-16K.f16.gguf new file mode 100644 index 0000000..aa6c98f --- /dev/null +++ b/Yi-1.5-9B-Chat-16K.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6346581faeade90f24ddd2206adf3cac5382727fc9d5f70d5baa6afef034cd66 +size 17661113120