commit eabacd278dade4720a16c923425e880c313d98a9 Author: ModelHub XC Date: Wed Jul 15 02:06:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Tele-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0284b3c --- /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-Tele.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Tele.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3e34c5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: AliMaatouk/TinyLlama-1.1B-Tele +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nlp +--- +## About + + + + + + +static quants of https://huggingface.co/AliMaatouk/TinyLlama-1.1B-Tele + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-1.1B-Tele-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-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Tele-GGUF/resolve/main/TinyLlama-1.1B-Tele.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-Tele.IQ4_XS.gguf b/TinyLlama-1.1B-Tele.IQ4_XS.gguf new file mode 100644 index 0000000..cb93759 --- /dev/null +++ b/TinyLlama-1.1B-Tele.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e29500d5bfe55198a0a0fd6c408b9410df3c0bb58f0e4f276f1bf2c1b09b84 +size 609807872 diff --git a/TinyLlama-1.1B-Tele.Q2_K.gguf b/TinyLlama-1.1B-Tele.Q2_K.gguf new file mode 100644 index 0000000..bcc7ed7 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8839807011813954cc2d3050bdbb23cb5a50c7e7de9ca280bdfc1818b786405f +size 432131584 diff --git a/TinyLlama-1.1B-Tele.Q3_K_L.gguf b/TinyLlama-1.1B-Tele.Q3_K_L.gguf new file mode 100644 index 0000000..10e2a54 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b07cdbf6bcce61ee558ad4c1a8b4f992df08aaff4eb8647667206a105285e30 +size 591527424 diff --git a/TinyLlama-1.1B-Tele.Q3_K_M.gguf b/TinyLlama-1.1B-Tele.Q3_K_M.gguf new file mode 100644 index 0000000..45cc50a --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7beb34046b28f3f9c1fba7902adafcf93e88b7be7bd3a8ef5f5d20300cc2283 +size 548404736 diff --git a/TinyLlama-1.1B-Tele.Q3_K_S.gguf b/TinyLlama-1.1B-Tele.Q3_K_S.gguf new file mode 100644 index 0000000..70c2cd2 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f2cc58647bfe4ee4fcaa9770bf44119b0568ade4ffe8068bb04ca4496e6a80 +size 499342848 diff --git a/TinyLlama-1.1B-Tele.Q4_K_M.gguf b/TinyLlama-1.1B-Tele.Q4_K_M.gguf new file mode 100644 index 0000000..5333f8e --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:938979daf9ddfbf3aa5fd5f867d5b7c97b7e0ea948103b6e01c8c2e8fc8fd17a +size 667815424 diff --git a/TinyLlama-1.1B-Tele.Q4_K_S.gguf b/TinyLlama-1.1B-Tele.Q4_K_S.gguf new file mode 100644 index 0000000..375c204 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9cd80f2c4eee1e93b07fe6e0f1147e84c179ba6ea03b79fd98a21b719d835da +size 639872512 diff --git a/TinyLlama-1.1B-Tele.Q5_K_M.gguf b/TinyLlama-1.1B-Tele.Q5_K_M.gguf new file mode 100644 index 0000000..583938c --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b50fd078daa2655529e78981e8ad37b49df45895ae9e9a5309476ad7c64ec2d +size 782044672 diff --git a/TinyLlama-1.1B-Tele.Q5_K_S.gguf b/TinyLlama-1.1B-Tele.Q5_K_S.gguf new file mode 100644 index 0000000..a2bc150 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849bf4e991c6016b7139fb8c48eee6fb3bc868632bc6dc6eb4aefa2a588aefad +size 766029312 diff --git a/TinyLlama-1.1B-Tele.Q6_K.gguf b/TinyLlama-1.1B-Tele.Q6_K.gguf new file mode 100644 index 0000000..efd4319 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00278e3f7e93d2b9ff8b3a280575cbe8e779c91515b51bad966098e0548dc9f +size 903413248 diff --git a/TinyLlama-1.1B-Tele.Q8_0.gguf b/TinyLlama-1.1B-Tele.Q8_0.gguf new file mode 100644 index 0000000..dc699a9 --- /dev/null +++ b/TinyLlama-1.1B-Tele.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0931022d04dbc935fce4ec31a90632bbdfac9115cff361fd8aef6b8a320bda2a +size 1169808896 diff --git a/TinyLlama-1.1B-Tele.f16.gguf b/TinyLlama-1.1B-Tele.f16.gguf new file mode 100644 index 0000000..79fafb7 --- /dev/null +++ b/TinyLlama-1.1B-Tele.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd93967e31b9c5563894ef031c04f469d5da0fc9959896003d3f7132a16bf1c5 +size 2201017856