commit ebb919044c874a3082f428cc13d3476506626f5b Author: ModelHub XC Date: Mon May 4 19:51:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..946b7a9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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-Alpaca-QLoRA.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Alpaca-QLoRA.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc4b8c6 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: sarimahsan101/TinyLlama-1.1B-Alpaca-QLoRA +datasets: +- tatsu-lab/alpaca +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- causal-lm +- qlora +- lora +- peft +- fine-tuned +- alpaca +- instruction-following +- tinyllama +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/sarimahsan101/TinyLlama-1.1B-Alpaca-QLoRA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-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-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_M.gguf) | i1-IQ2_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K.gguf) | i1-Q2_K | 0.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_S.gguf) | i1-IQ3_S | 0.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_M.gguf) | i1-IQ3_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_0.gguf) | i1-Q4_0 | 0.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_1.gguf) | i1-Q4_1 | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF/resolve/main/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q6_K.gguf) | i1-Q6_K | 1.0 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_M.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_M.gguf new file mode 100644 index 0000000..c5966a4 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fe8717ef071ce24e9fd48edc5cc40e7d65892bafb2c639d114405e777704e0 +size 289702880 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_S.gguf new file mode 100644 index 0000000..793aa77 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2449a020f50d83eff32b59f9f8195a589bc8b1c6853394f77a64e34cd9ae9779 +size 269968352 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_M.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_M.gguf new file mode 100644 index 0000000..ab8123b --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be2bf7372b76601ca03f58a943b6e186d44a7a9f2cac9844abc6c9b9e44dd7b +size 400077792 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_S.gguf new file mode 100644 index 0000000..bc5ee7c --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e67cee3ac345e420267e687c7a040668cca7fdf066d8aaac011e07334d156d +size 373765088 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XS.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a217514 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7d1b509ed0da2632fdd889ab6d1d71cca781c9447acb40df3fe0e72b4ebb5e +size 351790048 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XXS.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..54d447a --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d28a845af2447ba51b07fa9ea34b05b574acfcd8b09db7f8fe2beae9fb81407 +size 322593760 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_M.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_M.gguf new file mode 100644 index 0000000..57b4ffa --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e2e4cd04e40c45d2618981e8c8b8bcf433de72fad1551dfff63b7eb84bbb03 +size 516195296 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_S.gguf new file mode 100644 index 0000000..0989d11 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd092495474e9bf06c1c528abb516291e80e7fe68ef8b395cc5bca24cf11f913 +size 500876256 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XS.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8cb03da --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235a7017d18298a0e92d3c7e31f57d7a875d722cd96fa92cbed1847d59074477 +size 477627360 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XXS.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c025f2a --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e06b05988726824cbe67081755a028ac83216eafd96302b514e9a362ae97c9d +size 445133792 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_NL.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3330060 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2443e38b2ced56c88b6c70710cf7ed2d8884d9195b37b0fe3cb484683b731468 +size 638170080 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_XS.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fc999fc --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049c46a3cb4b547ad460e8c123627f438eeb8ccb9bb81cfaf720b3eb32fdbf02 +size 606204896 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K.gguf new file mode 100644 index 0000000..d865baa --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6c3aafb35da621b5b60306ed4e474fe603e52e4df9ad0c76e7ecb140450a52 +size 432133088 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dc9043d --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8eb0883c25f3d5584468e6e5942459092dbc6921835c719c823931ba0d3887 +size 402396128 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_L.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_L.gguf new file mode 100644 index 0000000..80ab31f --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bdf73fb1df23927d96c39a59068a50b7f7d2a011295eddab220b444bc3b965b +size 591528928 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_M.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_M.gguf new file mode 100644 index 0000000..97167cf --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a16371287d2779807464fc81b0e0f17470349e39c0bb8affcd2119e188576b +size 548406240 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3925cea --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b7feabb775310567ff2a6af63a36b4cb7f418f6f5e7329bbf22624fe547f95 +size 499344352 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_0.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_0.gguf new file mode 100644 index 0000000..cf237bc --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7968005f14658c1a10b84d38aefabf5defa52d949313a703de5118bcb2695c78 +size 638170080 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_1.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_1.gguf new file mode 100644 index 0000000..b9d00c6 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8727ebfb59fcc9746a0b3d0d2458b99a3887d8853bc6eb17f552762365e8d9b8 +size 701379552 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_M.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6956f23 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22a1895e86ae315c15f27c40c5f13b6e489a98cb4038836d9cbc23fbd2d6aeb7 +size 667816928 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_S.gguf new file mode 100644 index 0000000..80f0717 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810dbf660f8a07a3b0da1b83155a325cd4d1f03b5de44cbf98dd1dc20ebe8fe2 +size 639874016 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_M.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_M.gguf new file mode 100644 index 0000000..1c87f10 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b29fb19f091e86f63824b57705fb0eac9bc89d478418c3305e06c964d34430c +size 782046176 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_S.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9ceef39 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214fdb93dd4b02f7be98a56c61d2c7f77bb19796c6866828c84b518e6d45bdd5 +size 766030816 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q6_K.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q6_K.gguf new file mode 100644 index 0000000..979249f --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcc62ca73cdc97ad71d76c0ecba3583723778821aa7a2337c0f40626ee290346 +size 903414752 diff --git a/TinyLlama-1.1B-Alpaca-QLoRA.imatrix.gguf b/TinyLlama-1.1B-Alpaca-QLoRA.imatrix.gguf new file mode 100644 index 0000000..a6b6820 --- /dev/null +++ b/TinyLlama-1.1B-Alpaca-QLoRA.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782a32d115bed28eb6e8c0756ca97b7538d08ffdfba5b7532be9daae6827774e +size 1600704