commit 660db3fa387292e49e28a9155de205150d31bd03 Author: ModelHub XC Date: Fri Oct 9 23:54:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7891e55 --- /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 +Loquace-Tiny-ITA-1.1B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Loquace-Tiny-ITA-1.1B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.IQ4_XS.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..6b2719d --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b3fc6d1c623dd98fb3a08388a4854967d13de07d504b1ddbaadcf76e549ce6 +size 609808128 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q2_K.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..c1eefb6 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75382e7855c954fde1b6cd34bd9a71e5add8cb9e496744312ab7e58a742ef5f2 +size 432131840 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_L.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..a4db379 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffffb2027967273590fa2628a2f0fccdb555b0477c8ffb1a54cbd5230470b0f8 +size 591527680 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_M.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..aad1c2c --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3266b2c0d829e049f346ee2467ae88bdbb582556e5fa7bb0136d82f02dfe38 +size 548404992 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_S.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..9f4e47f --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a320e585809e3f29a436ab1e6c26281f53f0b98d2f0489dd9344a51a360a010 +size 499343104 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_M.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..b611466 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d91b045833e9004672fa30e3300e323beb0554ec46122bf222eda7329d8ec3 +size 667815680 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_S.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..399a8f0 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff69afae75ba01cbcb5349bab97f66c78d93cf6bccad6dc3e473521f3bd4ab7 +size 639872768 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_M.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..d47c652 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01f9f57f67ce37a7af6c8248831be4310e004977f5b8602528df7eeff0b0d1a +size 782044928 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_S.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..5f8c52c --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75fb40885ba7c37721359ea3a0e69b35239fa31081b70e111cd7a674a7be6ca8 +size 766029568 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q6_K.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..28a552d --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b356b977039670ed98f45b98de615c00fdc077e0778bd4ffc9ba579103478c4 +size 903413504 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.Q8_0.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..2028cb9 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b519139f634e21fae323b0d9ecc6657738b87c4a02a6fc69ec15c43c756fab12 +size 1169809152 diff --git a/Loquace-Tiny-ITA-1.1B-v0.1.f16.gguf b/Loquace-Tiny-ITA-1.1B-v0.1.f16.gguf new file mode 100644 index 0000000..2e30393 --- /dev/null +++ b/Loquace-Tiny-ITA-1.1B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc478c2fdb530e1c2f22fdcbe8eb4d08fd88fa4ba7dcfb73eeb98c757a1f048 +size 2201018112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca21bf7 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: cosimoiaia/Loquace-Tiny-ITA-1.1B-v0.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/cosimoiaia/Loquace-Tiny-ITA-1.1B-v0.1 + + +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/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Loquace-Tiny-ITA-1.1B-v0.1-GGUF/resolve/main/Loquace-Tiny-ITA-1.1B-v0.1.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. + +