commit 3b6938d85145020a89b523be11256d681def31d3 Author: ModelHub XC Date: Sun Aug 30 08:24:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tinyllama-roleplay-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..26e49af --- /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-roleplay.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-roleplay.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..143e706 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: 2kfi/tinyllama-roleplay +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/2kfi/tinyllama-roleplay + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#tinyllama-roleplay-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/tinyllama-roleplay-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-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-roleplay-GGUF/resolve/main/tinyllama-roleplay.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-roleplay.IQ4_XS.gguf b/tinyllama-roleplay.IQ4_XS.gguf new file mode 100644 index 0000000..ae99c0a --- /dev/null +++ b/tinyllama-roleplay.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79323be7b7c22f39f51019cf18988e0ec9a6f8bfe852089f8c429ab3505e6bf4 +size 609808288 diff --git a/tinyllama-roleplay.Q2_K.gguf b/tinyllama-roleplay.Q2_K.gguf new file mode 100644 index 0000000..a586ee4 --- /dev/null +++ b/tinyllama-roleplay.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb9598c3596ad0d57bf8882a816e198d7cefdfc8f68eba6630dc2c7fae65e55 +size 432132000 diff --git a/tinyllama-roleplay.Q3_K_L.gguf b/tinyllama-roleplay.Q3_K_L.gguf new file mode 100644 index 0000000..903c226 --- /dev/null +++ b/tinyllama-roleplay.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae30f72c8a73881fdb305795ebc57d6feb4b8b3675510537e901b1f05cc3fcb4 +size 591527840 diff --git a/tinyllama-roleplay.Q3_K_M.gguf b/tinyllama-roleplay.Q3_K_M.gguf new file mode 100644 index 0000000..5f69e52 --- /dev/null +++ b/tinyllama-roleplay.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3746bee0a96c2dbcaa6ed288957a59e344d15e2d552fe1b2463132c46541ad2 +size 548405152 diff --git a/tinyllama-roleplay.Q3_K_S.gguf b/tinyllama-roleplay.Q3_K_S.gguf new file mode 100644 index 0000000..0ccf84b --- /dev/null +++ b/tinyllama-roleplay.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf24a8c0b5192dfefdf87a8a105301f87c2633facb5d76fb8b6d16647fd63de +size 499343264 diff --git a/tinyllama-roleplay.Q4_K_M.gguf b/tinyllama-roleplay.Q4_K_M.gguf new file mode 100644 index 0000000..d693051 --- /dev/null +++ b/tinyllama-roleplay.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedfc1a6d4994e3e23f5106ddf8e04fdbcf216d6b568d2b9ad196f6ea7022f49 +size 667815840 diff --git a/tinyllama-roleplay.Q4_K_S.gguf b/tinyllama-roleplay.Q4_K_S.gguf new file mode 100644 index 0000000..201de0a --- /dev/null +++ b/tinyllama-roleplay.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7a44a4947fa29efb429eecccbc10ac1095c0b6f714dddbba6853f3484e93d4 +size 639872928 diff --git a/tinyllama-roleplay.Q5_K_M.gguf b/tinyllama-roleplay.Q5_K_M.gguf new file mode 100644 index 0000000..04e785d --- /dev/null +++ b/tinyllama-roleplay.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78e38b27938b5adbef53b3fc483990fcf6442bd3a597cd55c995bb71542e8a5 +size 782045088 diff --git a/tinyllama-roleplay.Q5_K_S.gguf b/tinyllama-roleplay.Q5_K_S.gguf new file mode 100644 index 0000000..97ec61b --- /dev/null +++ b/tinyllama-roleplay.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cea8b1f4f5f021bc327dc35a1a7e09abe548fea16d8bfed7166a438c5b5dbe4 +size 766029728 diff --git a/tinyllama-roleplay.Q6_K.gguf b/tinyllama-roleplay.Q6_K.gguf new file mode 100644 index 0000000..8a28d37 --- /dev/null +++ b/tinyllama-roleplay.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f6c1b3bb9bf011af288e02f16f0481c91e06449925c413dc868c1efb91a255 +size 903413664 diff --git a/tinyllama-roleplay.Q8_0.gguf b/tinyllama-roleplay.Q8_0.gguf new file mode 100644 index 0000000..befa046 --- /dev/null +++ b/tinyllama-roleplay.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd3e0b9d8774fe30569829ebb5f6cb7c853983f122afa2f66f0f314d7213f05 +size 1169809312 diff --git a/tinyllama-roleplay.f16.gguf b/tinyllama-roleplay.f16.gguf new file mode 100644 index 0000000..8f57c3a --- /dev/null +++ b/tinyllama-roleplay.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3120d0d5dfc35c3b627a8c1e20279f67e632e0f4f56f1385a510ff63a99724d8 +size 2201018272