commit cbfd65a4abfe368afc62579f6f6990ec5c4122e0 Author: ModelHub XC Date: Fri Sep 11 02:02:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama_v1.1_chinese-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a80000 --- /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 +TinyLlama_v1.1_chinese.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama_v1.1_chinese.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8989d7d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: TinyLlama/TinyLlama_v1.1_chinese +datasets: +- cerebras/SlimPajama-627B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TinyLlama/TinyLlama_v1.1_chinese + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama_v1.1_chinese-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-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/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama_v1.1_chinese-GGUF/resolve/main/TinyLlama_v1.1_chinese.f16.gguf) | f16 | 2.3 | 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/TinyLlama_v1.1_chinese.IQ4_XS.gguf b/TinyLlama_v1.1_chinese.IQ4_XS.gguf new file mode 100644 index 0000000..ca3e18c --- /dev/null +++ b/TinyLlama_v1.1_chinese.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ed19caf2e98d943f0320e8082f22334d5799d397de77eb4928ee0ffd5b578d +size 609807840 diff --git a/TinyLlama_v1.1_chinese.Q2_K.gguf b/TinyLlama_v1.1_chinese.Q2_K.gguf new file mode 100644 index 0000000..2901c3f --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44002938b780ea73dcf3b5f2c099b27be47004fe14305627c3fe30a0c2b000da +size 432131552 diff --git a/TinyLlama_v1.1_chinese.Q3_K_L.gguf b/TinyLlama_v1.1_chinese.Q3_K_L.gguf new file mode 100644 index 0000000..7432499 --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:940891541b0a65db29aad33ec4d97b49730e88cf96d2aabc0f8904cfd0f3610f +size 591527392 diff --git a/TinyLlama_v1.1_chinese.Q3_K_M.gguf b/TinyLlama_v1.1_chinese.Q3_K_M.gguf new file mode 100644 index 0000000..a06a3bb --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b385226ca3c852456f55eba6fa04c09b2a53300cfb478f9b60a14ab5c564551d +size 548404704 diff --git a/TinyLlama_v1.1_chinese.Q3_K_S.gguf b/TinyLlama_v1.1_chinese.Q3_K_S.gguf new file mode 100644 index 0000000..8349664 --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee450c7fb4ea6d7cbda6ab9363c0288e123b8900cf94351213df4d03bc38f4f +size 499342816 diff --git a/TinyLlama_v1.1_chinese.Q4_K_M.gguf b/TinyLlama_v1.1_chinese.Q4_K_M.gguf new file mode 100644 index 0000000..976834b --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b3a0ef511f2ca45b77add576ecc191bfaecb91ed948f36703c7c193a425bd8 +size 667815392 diff --git a/TinyLlama_v1.1_chinese.Q4_K_S.gguf b/TinyLlama_v1.1_chinese.Q4_K_S.gguf new file mode 100644 index 0000000..832a21f --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f363458c6ebfb3e171c61d29133ffda331a38296cd806dd44c66e2ed0a6dbbdd +size 639872480 diff --git a/TinyLlama_v1.1_chinese.Q5_K_M.gguf b/TinyLlama_v1.1_chinese.Q5_K_M.gguf new file mode 100644 index 0000000..2ea4ac3 --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3cf19005294d6e7db2a6d6d7ca3a0a6cbc05ab7a107a9f581a92e6127ad157d +size 782044640 diff --git a/TinyLlama_v1.1_chinese.Q5_K_S.gguf b/TinyLlama_v1.1_chinese.Q5_K_S.gguf new file mode 100644 index 0000000..f061704 --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc2c6c1c57c639eb0590fab9b22ff14d7e67dc5b958502c5fb8add5b3bc72ea +size 766029280 diff --git a/TinyLlama_v1.1_chinese.Q6_K.gguf b/TinyLlama_v1.1_chinese.Q6_K.gguf new file mode 100644 index 0000000..bb96c73 --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a5b8bcd5685273a811daf64daff9d40509b5254fd480ae57d08107ef8f6164 +size 903413216 diff --git a/TinyLlama_v1.1_chinese.Q8_0.gguf b/TinyLlama_v1.1_chinese.Q8_0.gguf new file mode 100644 index 0000000..572d53d --- /dev/null +++ b/TinyLlama_v1.1_chinese.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2572862611d2c94c378b176739885ee895a9e63411b11c97e909885c885bd4e3 +size 1169808864 diff --git a/TinyLlama_v1.1_chinese.f16.gguf b/TinyLlama_v1.1_chinese.f16.gguf new file mode 100644 index 0000000..5bcf0e9 --- /dev/null +++ b/TinyLlama_v1.1_chinese.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84fa94d7a47c1ca5b509812268804809a86ee95477ff43231602e5731ebbc70 +size 2201017824