commit 0d2843324b975d5c3e90d355ff5a88cf57e3ccae Author: ModelHub XC Date: Thu Jun 11 15:48:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Yi-Coder-9B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..720a98a --- /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-Coder-9B-Chat.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-9B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-Coder-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..b2bfa3a --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: 01-ai/Yi-Coder-9B-Chat +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/01-ai/Yi-Coder-9B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-Coder-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-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.IQ3_XS.gguf) | IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.IQ3_S.gguf) | IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.IQ3_M.gguf) | IQ3_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q5_K_S.gguf) | Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q5_K_M.gguf) | Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-9B-Chat.Q8_0.gguf) | Q8_0 | 9.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-Coder-9B-Chat-GGUF/resolve/main/Yi-Coder-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-Coder-9B-Chat.IQ3_M.gguf b/Yi-Coder-9B-Chat.IQ3_M.gguf new file mode 100644 index 0000000..9c6bb83 --- /dev/null +++ b/Yi-Coder-9B-Chat.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff6db2a31089559e77bb45d9863433babf4c37767990c6345062712b42f3b3b +size 4055462880 diff --git a/Yi-Coder-9B-Chat.IQ3_S.gguf b/Yi-Coder-9B-Chat.IQ3_S.gguf new file mode 100644 index 0000000..ab5f60f --- /dev/null +++ b/Yi-Coder-9B-Chat.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21da380a3acc6c6758b341ad01fd0f61e96046f7290193b869f9d76810aa227 +size 3912578016 diff --git a/Yi-Coder-9B-Chat.IQ3_XS.gguf b/Yi-Coder-9B-Chat.IQ3_XS.gguf new file mode 100644 index 0000000..8bea06e --- /dev/null +++ b/Yi-Coder-9B-Chat.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87258f91fb0a1b3e21820816f7208c85cdca6a4545db91eb8e01603fcfa26aba +size 3717936096 diff --git a/Yi-Coder-9B-Chat.IQ4_XS.gguf b/Yi-Coder-9B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..c7f0aec --- /dev/null +++ b/Yi-Coder-9B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eae7485be6a64c2ec53b3a918a39f74c9cd40219e531e5c374085b3791ee83c +size 4827280352 diff --git a/Yi-Coder-9B-Chat.Q2_K.gguf b/Yi-Coder-9B-Chat.Q2_K.gguf new file mode 100644 index 0000000..6e29c96 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de0baf91b8ffc0aca7c491a32230161c027ecaf45e22a29a4952cde67559ff6 +size 3354325984 diff --git a/Yi-Coder-9B-Chat.Q3_K_L.gguf b/Yi-Coder-9B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..2027d5c --- /dev/null +++ b/Yi-Coder-9B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8208055c7b30fd0c4978ef3b7388947e5e7d2fdf25b46f847b02c84f323a39 +size 4690752480 diff --git a/Yi-Coder-9B-Chat.Q3_K_M.gguf b/Yi-Coder-9B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..c22d61b --- /dev/null +++ b/Yi-Coder-9B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20c15a2a5a56e9433c37453d396d6f85235a09c6bcafe2f092c1b566f7990cb +size 4324406240 diff --git a/Yi-Coder-9B-Chat.Q3_K_S.gguf b/Yi-Coder-9B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..5469ec6 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472410e754196749d94ec97df9bde7208eb0976bd88ca9bb784f12fdd328807d +size 3899208672 diff --git a/Yi-Coder-9B-Chat.Q4_K_M.gguf b/Yi-Coder-9B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..d3b5cdf --- /dev/null +++ b/Yi-Coder-9B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7cb1a43316b5af93375f152303a9bae36d669eae2b187800b202bb730a46c0 +size 5328958432 diff --git a/Yi-Coder-9B-Chat.Q4_K_S.gguf b/Yi-Coder-9B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..f37a460 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46de31e8da2de1f6e61635b730429a8d977cb47327b57c228ef0e1528ac5bf03 +size 5071860704 diff --git a/Yi-Coder-9B-Chat.Q5_K_M.gguf b/Yi-Coder-9B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..84442e1 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0d7686dc1fbc67d86bc245409b6196d67776bd2d62559b84e387512c4f1518 +size 6258258912 diff --git a/Yi-Coder-9B-Chat.Q5_K_S.gguf b/Yi-Coder-9B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..51c2544 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70b26fb48dd5490b07602d7b88763d9df55e701bd367ec8577dbb5d135b1613 +size 6107853792 diff --git a/Yi-Coder-9B-Chat.Q6_K.gguf b/Yi-Coder-9B-Chat.Q6_K.gguf new file mode 100644 index 0000000..26bd2c1 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e109d32e3615f503bb57b5ec6b2ea4776a47582b6c6c5bea54cd1e92cc696e7e +size 7245640672 diff --git a/Yi-Coder-9B-Chat.Q8_0.gguf b/Yi-Coder-9B-Chat.Q8_0.gguf new file mode 100644 index 0000000..6bf9599 --- /dev/null +++ b/Yi-Coder-9B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ddcc05d325787b2c906345a65f79d95eec923b8ccd2c9f0e7d548d29cfe9808 +size 9383916512 diff --git a/Yi-Coder-9B-Chat.f16.gguf b/Yi-Coder-9B-Chat.f16.gguf new file mode 100644 index 0000000..d9730e3 --- /dev/null +++ b/Yi-Coder-9B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2b65de45be4be5b01eda0b16a8b14ba3780b3532cb57369c423847e31f72d4 +size 17661113312