commit a230f2526a6d659297d225c4f5aa63a9968161a6 Author: ModelHub XC Date: Sun Jun 21 14:16:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4033331 --- /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-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f4d2c52 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: LlamaFinetuneBase/TinyLlama-1.1B-Instruct +datasets: +- cerebras/SlimPajama-627B +- bigcode/starcoderdata +- HuggingFaceH4/ultrachat_200k +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/LlamaFinetuneBase/TinyLlama-1.1B-Instruct + + +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-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.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-Instruct.IQ4_XS.gguf b/TinyLlama-1.1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..bf0e08a --- /dev/null +++ b/TinyLlama-1.1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3dad4d49bce7192ac18723c9e52a6ed62614132095e58f65b0cc0b12b943af +size 609809024 diff --git a/TinyLlama-1.1B-Instruct.Q2_K.gguf b/TinyLlama-1.1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..cff9251 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fde9a53efa3b7f1e3243489b42de168faa3fb24e332f5eebeddd2c4d16ec442 +size 432132736 diff --git a/TinyLlama-1.1B-Instruct.Q3_K_L.gguf b/TinyLlama-1.1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..908e691 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aacb139ffafc20fbd074a33c3dc45034e51643fdfc5874dcd533680c3d4d0d66 +size 591528576 diff --git a/TinyLlama-1.1B-Instruct.Q3_K_M.gguf b/TinyLlama-1.1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ceaaf72 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f0b56ffe9cae9b73d61a79e7598b2527e5608760446e78eac4d6f0f0a415e59 +size 548405888 diff --git a/TinyLlama-1.1B-Instruct.Q3_K_S.gguf b/TinyLlama-1.1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..f331654 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec60bdb275eb9f801f14a869440a52379cf3c503dba06b1b2f30525cea8c01f +size 499344000 diff --git a/TinyLlama-1.1B-Instruct.Q4_K_M.gguf b/TinyLlama-1.1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..4cf65a2 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445160b724c92ad89a52a132b29905f6026e61c9c75e487c5aa8a5e7dda3749a +size 667816576 diff --git a/TinyLlama-1.1B-Instruct.Q4_K_S.gguf b/TinyLlama-1.1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..3c67d63 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2290d3e1df642f4a8745f727fafef2acf7396097610fdb0993ef070ad1101e0d +size 639873664 diff --git a/TinyLlama-1.1B-Instruct.Q5_K_M.gguf b/TinyLlama-1.1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..1d6cf68 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2362ac1b650721c113a645cc36ff4326b9f121bbd3fe14e158f46f9f9f1f6876 +size 782045824 diff --git a/TinyLlama-1.1B-Instruct.Q5_K_S.gguf b/TinyLlama-1.1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..65bc20f --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29759fa752b760bb6ff26a81316abc407dec57c77a35f9305807ff45d85e249 +size 766030464 diff --git a/TinyLlama-1.1B-Instruct.Q6_K.gguf b/TinyLlama-1.1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..519dbf2 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c134946f8d4685cceec6884c77f5e12a9b39866fbf7c0569d2d2f5543a90e4be +size 903414400 diff --git a/TinyLlama-1.1B-Instruct.Q8_0.gguf b/TinyLlama-1.1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..eb1b24e --- /dev/null +++ b/TinyLlama-1.1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a547fec469908942db178b03808c0d42d0283511fb8587fa8846f48d5be455f +size 1169810048 diff --git a/TinyLlama-1.1B-Instruct.f16.gguf b/TinyLlama-1.1B-Instruct.f16.gguf new file mode 100644 index 0000000..71a97d4 --- /dev/null +++ b/TinyLlama-1.1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb92b3587eaab28c9384701b5453c7c7c1006fb4d4e06b22a795f3ecd466d480 +size 2201019008