commit 0f21a07b4e385d7e25195465637c2c0910778e25 Author: ModelHub XC Date: Tue Jun 2 17:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tinyllama-chatbot-merged-v4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ddf66c9 --- /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-chatbot-merged-v4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-chatbot-merged-v4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..aaf42fa --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: tmd-rahul/tinyllama-chatbot-merged-v4 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/tmd-rahul/tinyllama-chatbot-merged-v4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#tinyllama-chatbot-merged-v4-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-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-chatbot-merged-v4-GGUF/resolve/main/tinyllama-chatbot-merged-v4.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-chatbot-merged-v4.IQ4_XS.gguf b/tinyllama-chatbot-merged-v4.IQ4_XS.gguf new file mode 100644 index 0000000..9425074 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc81ca0bd86511aaea058b882234ce16e737905341f72c628ae5818982ce41a +size 609808256 diff --git a/tinyllama-chatbot-merged-v4.Q2_K.gguf b/tinyllama-chatbot-merged-v4.Q2_K.gguf new file mode 100644 index 0000000..b9e532d --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6e2955e38ee8b2bee264c5934f59e92beb5bb373bf179e63d6f7ebd845b8cb +size 432131968 diff --git a/tinyllama-chatbot-merged-v4.Q3_K_L.gguf b/tinyllama-chatbot-merged-v4.Q3_K_L.gguf new file mode 100644 index 0000000..44846c1 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2231142084b311a18a6015926a0c86ce5fdbfb88825ed62207569fa8e592504 +size 591527808 diff --git a/tinyllama-chatbot-merged-v4.Q3_K_M.gguf b/tinyllama-chatbot-merged-v4.Q3_K_M.gguf new file mode 100644 index 0000000..528d0ef --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1620edfd596d268ea97a35118f0578ba7d224a8ad76822e3177b3b6e10cc6d8 +size 548405120 diff --git a/tinyllama-chatbot-merged-v4.Q3_K_S.gguf b/tinyllama-chatbot-merged-v4.Q3_K_S.gguf new file mode 100644 index 0000000..7a5e790 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9dd1a203e476d2d04945771f93e04a3d3b506f8da0c3419e323ea831eaaecc4 +size 499343232 diff --git a/tinyllama-chatbot-merged-v4.Q4_K_M.gguf b/tinyllama-chatbot-merged-v4.Q4_K_M.gguf new file mode 100644 index 0000000..3d10a47 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c738e12374f53853fe02f4f39186b3279e2c85e3e103e4226fecf919d10789a +size 667815808 diff --git a/tinyllama-chatbot-merged-v4.Q4_K_S.gguf b/tinyllama-chatbot-merged-v4.Q4_K_S.gguf new file mode 100644 index 0000000..fa580a4 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f61024d8b9167c9a3808ab931028ab3b0419bfe1e57fe8308849fcc658cdfc +size 639872896 diff --git a/tinyllama-chatbot-merged-v4.Q5_K_M.gguf b/tinyllama-chatbot-merged-v4.Q5_K_M.gguf new file mode 100644 index 0000000..2e15cf1 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd2ba70e4c229cfd5428f637f2a9d51e7d809a956b4b3156922f54730ca49002 +size 782045056 diff --git a/tinyllama-chatbot-merged-v4.Q5_K_S.gguf b/tinyllama-chatbot-merged-v4.Q5_K_S.gguf new file mode 100644 index 0000000..cfe87bb --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2aaf235834be93aef7e26f7ff46fb57a37654341ba0c255630e5be02049de9 +size 766029696 diff --git a/tinyllama-chatbot-merged-v4.Q6_K.gguf b/tinyllama-chatbot-merged-v4.Q6_K.gguf new file mode 100644 index 0000000..c9f1e11 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197f192cbb33faba3c12f685ec160ae3c40b1d8c6df10b2aae5b38e7bf4fe9f4 +size 903413632 diff --git a/tinyllama-chatbot-merged-v4.Q8_0.gguf b/tinyllama-chatbot-merged-v4.Q8_0.gguf new file mode 100644 index 0000000..8ca4ab8 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31cbd9217a3d67667b58e91f39681907b258b19b42daf5553ce54576038894b2 +size 1169809280 diff --git a/tinyllama-chatbot-merged-v4.f16.gguf b/tinyllama-chatbot-merged-v4.f16.gguf new file mode 100644 index 0000000..3e434b0 --- /dev/null +++ b/tinyllama-chatbot-merged-v4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2ad90e5c6682773a66d83adf26e98ef44a8c51568ae4d3e94cc3115dbc3f940 +size 2201018240