commit 4d5bbfdcc16e437ee8d7ebd9cc42e334eca29c11 Author: ModelHub XC Date: Thu Jun 4 20:28:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..faca297 --- /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-1.1B-Chat-SFT-alpaca-cleaned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..86c3a54 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: juweriya/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/juweriya/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned-GGUF/resolve/main/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.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-1.1B-Chat-SFT-alpaca-cleaned.IQ4_XS.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.IQ4_XS.gguf new file mode 100644 index 0000000..eb98a40 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf4a070310f39a4202d44d4f206de08fdbc2dfc8b9903023a77be87b7a3c03f +size 609808256 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q2_K.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q2_K.gguf new file mode 100644 index 0000000..34daa9b --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf4fc6f8bbe222ccb5432d530de13c8e7f6cd85b58cab22aaf08580d464bc9f +size 432131968 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_L.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_L.gguf new file mode 100644 index 0000000..bb52044 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f53aed49a86cf79ee95373e730f44edcc95242d390b6f95069d11f05d540c4c +size 591527808 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_M.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_M.gguf new file mode 100644 index 0000000..54822de --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193a857425243d6da3f85da29195a860f1ed7ed3081e114d756051d37bf15d63 +size 548405120 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_S.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_S.gguf new file mode 100644 index 0000000..b11454d --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254b703a02de60f9db8679abf3f4a2a6dcec6c49eb41c07f53d5bec6a30f1c57 +size 499343232 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_M.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_M.gguf new file mode 100644 index 0000000..20c0865 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36b6fee5fc19212dd5e94061cdaf44bf38209787ffdaf932574d7e2e5a388600 +size 667815808 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_S.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_S.gguf new file mode 100644 index 0000000..3d8f9f7 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63e1080cc9e903a639b2cb9429f123bedfc9eaf05c3aa3556b7c40869b9e4742 +size 639872896 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_M.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_M.gguf new file mode 100644 index 0000000..dec4308 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4493c6836db56c4997020f64ea43b2c9471362ada5558580e7650f67f9a24cd9 +size 782045056 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_S.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_S.gguf new file mode 100644 index 0000000..00cb6c8 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36abc814b6f91df83d04070773e474ad6bfe7667c098dbb4203bcdcb6f0791a4 +size 766029696 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q6_K.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q6_K.gguf new file mode 100644 index 0000000..52b7174 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d453ea970e269870d87e400d4f910ea37d92d6d25ada94734efaee5a8503a9f +size 903413632 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q8_0.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q8_0.gguf new file mode 100644 index 0000000..18dd31e --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b48bfba8f1cd6eaeb938896a2ae90996df65b1af1ce91431e8b0581c8440d6 +size 1169809280 diff --git a/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.f16.gguf b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.f16.gguf new file mode 100644 index 0000000..16e63b9 --- /dev/null +++ b/TinyLlama-1.1B-Chat-SFT-alpaca-cleaned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8746a95d5fa6ecf8602d017efc133632a19f364768d67ba5d36d8ac83905f54c +size 2201018240