commit 9f543471e119e1f6546ded5fcecd7c4447ea4779 Author: ModelHub XC Date: Thu Jun 4 01:31:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aitana-2B-SI-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..99f9508 --- /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 +Aitana-2B-SI-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aitana-2B-SI-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aitana-2B-SI-Instruct.IQ4_XS.gguf b/Aitana-2B-SI-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..d58d543 --- /dev/null +++ b/Aitana-2B-SI-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e91f7661fca107f5a30586077c5cd05eb317fbebf72b1515778b7ecc3d8e67 +size 1370142144 diff --git a/Aitana-2B-SI-Instruct.Q2_K.gguf b/Aitana-2B-SI-Instruct.Q2_K.gguf new file mode 100644 index 0000000..875d1d7 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb68f8c90dfbfa5f40167f7bb06dafe963194ddc1aec2d782681bfc83456289 +size 1087411648 diff --git a/Aitana-2B-SI-Instruct.Q3_K_L.gguf b/Aitana-2B-SI-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1b68fd6 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a51894ff69900beff1f52199a2dc0fc5de6c1bcb22106505c35fd21e5f11b0 +size 1317459392 diff --git a/Aitana-2B-SI-Instruct.Q3_K_M.gguf b/Aitana-2B-SI-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e0560fd --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159a7a03f2c6e13b9a2cc367550c658d22e07f45566d376f5ea3dc0071bfbc82 +size 1277326784 diff --git a/Aitana-2B-SI-Instruct.Q3_K_S.gguf b/Aitana-2B-SI-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..57a6f17 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0452cdc30275443c6b12dfabc8bf1a2e7bd0fadd9ed77f3bd2a6c03335eaf87 +size 1215419840 diff --git a/Aitana-2B-SI-Instruct.Q4_K_M.gguf b/Aitana-2B-SI-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..4df7b70 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3269a277b55edd0f9bbfdf359af1abab10ef8b873f0a65f2bd73c24cfa91494b +size 1506088384 diff --git a/Aitana-2B-SI-Instruct.Q4_K_S.gguf b/Aitana-2B-SI-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..3f5cd72 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63368f03d6e806e6376bfc764dd1b22be4440af87e5e8d7e890f8bc4c2df7608 +size 1447163328 diff --git a/Aitana-2B-SI-Instruct.Q5_K_M.gguf b/Aitana-2B-SI-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..f2f5e0c --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777f7ff89035cf9d9e66b24c769d6b757232fa7d33857e8a15577463da87b70c +size 1690867136 diff --git a/Aitana-2B-SI-Instruct.Q5_K_S.gguf b/Aitana-2B-SI-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..2c65886 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28c1cd7fc79d8d1259c028d95457475f59029f48d0017839e43769f6275a7d8 +size 1642403264 diff --git a/Aitana-2B-SI-Instruct.Q6_K.gguf b/Aitana-2B-SI-Instruct.Q6_K.gguf new file mode 100644 index 0000000..bcaec8a --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e13404d4d4ad6b00640f25abc85cdbfd5e07d814b5b7d2558cb14bda9afce4 +size 1920095680 diff --git a/Aitana-2B-SI-Instruct.Q8_0.gguf b/Aitana-2B-SI-Instruct.Q8_0.gguf new file mode 100644 index 0000000..be126e3 --- /dev/null +++ b/Aitana-2B-SI-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c61f3fe31c0f59e0b6945c8bfeb842c323dff88bc07e413ccc0c07421354b4 +size 2401080768 diff --git a/Aitana-2B-SI-Instruct.f16.gguf b/Aitana-2B-SI-Instruct.f16.gguf new file mode 100644 index 0000000..0e0df52 --- /dev/null +++ b/Aitana-2B-SI-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f006a0a4b98256bf8a01af4224b9346ff48bae642ab2f15c34869b61e0c76331 +size 4513633728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6ef18b9 --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ +--- +base_model: gplsi/Aitana-2B-SI-Instruct +datasets: +- OpenAssistant/oasst2 +- OpenAssistant/oasst1 +- BSC-LT/m-personas +- projecte-aina/RAG_Multilingual +- facebook/flores +- CohereLabs/aya_dataset +- Unbabel/TowerBlocks-v0.2 +- projecte-aina/MentorES +- databricks/databricks-dolly-15k +- tatsu-lab/alpaca +- openai/gsm8k +- Open-Orca/OpenOrca +- HuggingFaceH4/no_robots +- projecte-aina/CoQCat +- gplsi/boua_parallel +- allenai/scifact +- somosnlp/LingComp_QA +- somosnlp/instruct-legal-refugiados-es +language: +- ca +- es +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- valencian +- spanish +- english +- text-generation +- instruct +- alia +- gplsi +--- +## About + + + + + + + + + +static quants of https://huggingface.co/gplsi/Aitana-2B-SI-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Aitana-2B-SI-Instruct-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/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q6_K.gguf) | Q6_K | 2.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.Q8_0.gguf) | Q8_0 | 2.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aitana-2B-SI-Instruct-GGUF/resolve/main/Aitana-2B-SI-Instruct.f16.gguf) | f16 | 4.6 | 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. + +