commit fc8c871aae4bf59ebb5b5cbc4203ccf5d5dfc5fc Author: ModelHub XC Date: Tue Aug 18 22:07:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2dc9b9d --- /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 +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6ef339a --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Guilherme34/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Guilherme34/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized + + +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/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized-GGUF/resolve/main/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.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/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.IQ4_XS.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.IQ4_XS.gguf new file mode 100644 index 0000000..9832f86 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b254c763df67ef0086d7bda7ba75af83d8f62df5d207afc8080288ebd62cc7 +size 609807840 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q2_K.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q2_K.gguf new file mode 100644 index 0000000..175902e --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c4dafdc943246fb5bb23e4c3776a3c562b8765c47fc2a318b6995b4a0c59a9 +size 432131552 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_L.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_L.gguf new file mode 100644 index 0000000..000ddd4 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77662bc8b6edfd7c52df4697866dddf5975fa924708740400427b83a45f50a08 +size 591527392 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_M.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_M.gguf new file mode 100644 index 0000000..f614cc3 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b0c2ed30b04cd772360afa49ecc241e4ec813e49762d7d8c703574cb6695d3 +size 548404704 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_S.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_S.gguf new file mode 100644 index 0000000..819edfd --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e80c331424fb7a121e2da0a3ce0fe354cde7964df887df67092f28c4df14d1 +size 499342816 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_M.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_M.gguf new file mode 100644 index 0000000..b69ec0c --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82976dc8472318d1a567d6c72a16375d110682a14c763391bb933f9600a38da9 +size 667815392 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_S.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_S.gguf new file mode 100644 index 0000000..9aa87ff --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5eb9744c51cd4c37365f946d6f41f4609bea24c00b757fb8b7831665788785b +size 639872480 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_M.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_M.gguf new file mode 100644 index 0000000..7663131 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f0c29b98f060cf936a37f2d896ee049713cecc0f6a6bcdb9ce685496792126 +size 782044640 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_S.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_S.gguf new file mode 100644 index 0000000..8d36596 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4c9dad241676c9b53d04c4fce0c73b8a70f5be3565cb16af1e19ae06530035 +size 766029280 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q6_K.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q6_K.gguf new file mode 100644 index 0000000..fdb4167 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973d1e4e6122836563365926f70a5150674e25477a95bd25cfc967b09d800cd5 +size 903413216 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q8_0.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q8_0.gguf new file mode 100644 index 0000000..965f273 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0b59ed1977001545477e3d62aca1bcd29b48e35ded49343725a377aa55e773 +size 1169808864 diff --git a/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.f16.gguf b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.f16.gguf new file mode 100644 index 0000000..adebce2 --- /dev/null +++ b/Samantha-tinyllama-1.1b-v2-modelnotloranotquantized.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae73171592081c09f13ab7aa9d1947653c5005552d1cf85a0254d417da3dfd6 +size 2201017824