commit 1e461eb08cec6ebc332b24998fc87009f42f5a5b Author: ModelHub XC Date: Wed Apr 22 03:21:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Yi-6B-200K-Llama-sharded-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d729f24 --- /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 +Yi-6B-200K-Llama-sharded.f16.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-6B-200K-Llama-sharded.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2078419 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: pszemraj/Yi-6B-200K-Llama-sharded +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sharded +- yi +- bf16 +- colab +--- +## About + + + + + + + + + +static quants of https://huggingface.co/pszemraj/Yi-6B-200K-Llama-sharded + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Yi-6B-200K-Llama-sharded-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-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-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q2_K.gguf) | Q2_K | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q3_K_S.gguf) | Q3_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q3_K_L.gguf) | Q3_K_L | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.IQ4_XS.gguf) | IQ4_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q5_K_S.gguf) | Q5_K_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q5_K_M.gguf) | Q5_K_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q6_K.gguf) | Q6_K | 5.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-6B-200K-Llama-sharded-GGUF/resolve/main/Yi-6B-200K-Llama-sharded.f16.gguf) | f16 | 12.2 | 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. + + diff --git a/Yi-6B-200K-Llama-sharded.IQ4_XS.gguf b/Yi-6B-200K-Llama-sharded.IQ4_XS.gguf new file mode 100644 index 0000000..e54fc95 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ee66902f97b501a4d7c0d9d94ee3021ca04429cf55f9f4b339682daf18a88f +size 3336786240 diff --git a/Yi-6B-200K-Llama-sharded.Q2_K.gguf b/Yi-6B-200K-Llama-sharded.Q2_K.gguf new file mode 100644 index 0000000..4547781 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd281308f6653fa4ba8d256d087c290197247359af3bea2e0975afd53b9c5f3 +size 2337067328 diff --git a/Yi-6B-200K-Llama-sharded.Q3_K_L.gguf b/Yi-6B-200K-Llama-sharded.Q3_K_L.gguf new file mode 100644 index 0000000..4ee2243 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8f82c063d4be2474b5698297302b495e1af8a07c79f32cc0672ffac90a211e +size 3236892992 diff --git a/Yi-6B-200K-Llama-sharded.Q3_K_M.gguf b/Yi-6B-200K-Llama-sharded.Q3_K_M.gguf new file mode 100644 index 0000000..93cdea9 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b22d78c58a590e42f8e4dd9cf89e62dde37ef5af13f036eb676231200875dde +size 2992836928 diff --git a/Yi-6B-200K-Llama-sharded.Q3_K_S.gguf b/Yi-6B-200K-Llama-sharded.Q3_K_S.gguf new file mode 100644 index 0000000..26e3898 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18d8e4531b6c05abea0ec844fa08767379b2e74e27eeaf67d744f2803214786 +size 2709197120 diff --git a/Yi-6B-200K-Llama-sharded.Q4_K_M.gguf b/Yi-6B-200K-Llama-sharded.Q4_K_M.gguf new file mode 100644 index 0000000..600de7b --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf0d0a975b094717cbdf37eaa1f96fc19fe841bfdad3a25c7ff26db8939c6ca +size 3673968960 diff --git a/Yi-6B-200K-Llama-sharded.Q4_K_S.gguf b/Yi-6B-200K-Llama-sharded.Q4_K_S.gguf new file mode 100644 index 0000000..19d7b99 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00f8c2c48c162bb96c05eb8e43b84df99bbeb4f1e4af5c7b8c7e2009f88bcc2 +size 3502920000 diff --git a/Yi-6B-200K-Llama-sharded.Q5_K_M.gguf b/Yi-6B-200K-Llama-sharded.Q5_K_M.gguf new file mode 100644 index 0000000..92b1e3c --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480ebe582d8fdbc0a7dbec676f0acf23e037c925ef1d1dd950aa5c98a448ef1a +size 4304425280 diff --git a/Yi-6B-200K-Llama-sharded.Q5_K_S.gguf b/Yi-6B-200K-Llama-sharded.Q5_K_S.gguf new file mode 100644 index 0000000..84a39ea --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06418b28e99ee4a54078fcddaaffe2965e5f092b6b6189da8ddd691dd4176bb +size 4204155200 diff --git a/Yi-6B-200K-Llama-sharded.Q6_K.gguf b/Yi-6B-200K-Llama-sharded.Q6_K.gguf new file mode 100644 index 0000000..a5d7116 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98faba743be54faab00a3bdb88ef0c47b65d7aef9774e746a21e195cf063b059 +size 4974285120 diff --git a/Yi-6B-200K-Llama-sharded.Q8_0.gguf b/Yi-6B-200K-Llama-sharded.Q8_0.gguf new file mode 100644 index 0000000..018538b --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d01d8c1d0038fd4465cb8a0b3a6394c072083df7667d72417360018bf98852d +size 6442127680 diff --git a/Yi-6B-200K-Llama-sharded.f16.gguf b/Yi-6B-200K-Llama-sharded.f16.gguf new file mode 100644 index 0000000..880fe79 --- /dev/null +++ b/Yi-6B-200K-Llama-sharded.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43169f80813505bc019dca020be7b2aae37d78be700a6715c9419a1659dd2a93 +size 12124098880