commit 195e35dbc1f08f17485d44b1be6a5a53dce846ff Author: ModelHub XC Date: Wed Apr 22 10:37:49 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Altos-gemma-2b-ft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0cef95d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Altos-gemma-2b-ft.f16.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Altos-gemma-2b-ft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Altos-gemma-2b-ft.IQ3_M.gguf b/Altos-gemma-2b-ft.IQ3_M.gguf new file mode 100644 index 0000000..721b087 --- /dev/null +++ b/Altos-gemma-2b-ft.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62fcb6d44b5e4cf5903f35c8c1c898bcfb4124ae77289b5f194e73426a5f31f +size 1308173344 diff --git a/Altos-gemma-2b-ft.IQ3_S.gguf b/Altos-gemma-2b-ft.IQ3_S.gguf new file mode 100644 index 0000000..fe153a0 --- /dev/null +++ b/Altos-gemma-2b-ft.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6deafa362f2f06947ea6ea6ffd710341f9395b827fb7c6f45a80c6619fa5f66 +size 1289233440 diff --git a/Altos-gemma-2b-ft.IQ3_XS.gguf b/Altos-gemma-2b-ft.IQ3_XS.gguf new file mode 100644 index 0000000..82e1098 --- /dev/null +++ b/Altos-gemma-2b-ft.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1550bfa785ff9832da400ce04ed30d937aaf2090a719961d6cbf1ace7db2f418 +size 1244357664 diff --git a/Altos-gemma-2b-ft.IQ4_XS.gguf b/Altos-gemma-2b-ft.IQ4_XS.gguf new file mode 100644 index 0000000..5e6487b --- /dev/null +++ b/Altos-gemma-2b-ft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0be5c74a2ab7750fea466d35f961d1a81c7b6b3c8ea8c597a0ff51381006eb +size 1501217824 diff --git a/Altos-gemma-2b-ft.Q2_K.gguf b/Altos-gemma-2b-ft.Q2_K.gguf new file mode 100644 index 0000000..6412be7 --- /dev/null +++ b/Altos-gemma-2b-ft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f5cd1d5444b71036f4f9c287eccadc539996a0b2f72c14f676a039fbdf367bd +size 1157923872 diff --git a/Altos-gemma-2b-ft.Q3_K_L.gguf b/Altos-gemma-2b-ft.Q3_K_L.gguf new file mode 100644 index 0000000..abdf572 --- /dev/null +++ b/Altos-gemma-2b-ft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d8d37d9c335654d429522381dfb26ce3611135e4791e61723ca392ba72ac46 +size 1465590816 diff --git a/Altos-gemma-2b-ft.Q3_K_M.gguf b/Altos-gemma-2b-ft.Q3_K_M.gguf new file mode 100644 index 0000000..7d03755 --- /dev/null +++ b/Altos-gemma-2b-ft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e749c87442b721abb41ebbff9dbfb826e53c00547849e931d96e8f6502e1edc6 +size 1383801888 diff --git a/Altos-gemma-2b-ft.Q3_K_S.gguf b/Altos-gemma-2b-ft.Q3_K_S.gguf new file mode 100644 index 0000000..4aab4a1 --- /dev/null +++ b/Altos-gemma-2b-ft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b07c448d9cb76bd9869dd3ff5885d1a0f0186603d28e8f7a66e4d849d0aa73 +size 1287980064 diff --git a/Altos-gemma-2b-ft.Q4_K_M.gguf b/Altos-gemma-2b-ft.Q4_K_M.gguf new file mode 100644 index 0000000..ed9bdec --- /dev/null +++ b/Altos-gemma-2b-ft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2ae4569d61088ffd9eec9b5eb9a6cc673c4f6a7af563bf5966ec4791c63b76 +size 1630262304 diff --git a/Altos-gemma-2b-ft.Q4_K_S.gguf b/Altos-gemma-2b-ft.Q4_K_S.gguf new file mode 100644 index 0000000..fd6034f --- /dev/null +++ b/Altos-gemma-2b-ft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bba8304e05f2fd203114898eaf7b889883975a37e54e7314819a3541bf89871 +size 1559839776 diff --git a/Altos-gemma-2b-ft.Q5_K_M.gguf b/Altos-gemma-2b-ft.Q5_K_M.gguf new file mode 100644 index 0000000..499d385 --- /dev/null +++ b/Altos-gemma-2b-ft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2acd459f7bb76ac291821de18c5845c571ddb40bfc8e09ae14560a2c0ff4204f +size 1839649824 diff --git a/Altos-gemma-2b-ft.Q5_K_S.gguf b/Altos-gemma-2b-ft.Q5_K_S.gguf new file mode 100644 index 0000000..9ed98dc --- /dev/null +++ b/Altos-gemma-2b-ft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:163f0721fd80c831946f6eb7bb76e88df04a26df2619c7e7ed3b281a9585e192 +size 1798915104 diff --git a/Altos-gemma-2b-ft.Q6_K.gguf b/Altos-gemma-2b-ft.Q6_K.gguf new file mode 100644 index 0000000..6c45ced --- /dev/null +++ b/Altos-gemma-2b-ft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245e23610bed5461f9b3193075fac7a935c39c4b1d57f4d467a1a1b03b40713f +size 2062124064 diff --git a/Altos-gemma-2b-ft.Q8_0.gguf b/Altos-gemma-2b-ft.Q8_0.gguf new file mode 100644 index 0000000..eb3e7fc --- /dev/null +++ b/Altos-gemma-2b-ft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9af1bed9c94aafc6a5d0e45484bf77bd1b5b72eac75eb8d10fc1e1a587ef97ae +size 2669069344 diff --git a/Altos-gemma-2b-ft.f16.gguf b/Altos-gemma-2b-ft.f16.gguf new file mode 100644 index 0000000..55ebaa2 --- /dev/null +++ b/Altos-gemma-2b-ft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba8678a05a88c4f05090ac322bec440dcb3adaeafe2b0cc55688dbe65c0c5f7 +size 5018534944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cd4792a --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: VickyGenAi/Altos-gemma-2b-ft +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/VickyGenAi/Altos-gemma-2b-ft + + +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/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.IQ3_XS.gguf) | IQ3_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.IQ3_S.gguf) | IQ3_S | 1.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.IQ3_M.gguf) | IQ3_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Altos-gemma-2b-ft-GGUF/resolve/main/Altos-gemma-2b-ft.f16.gguf) | f16 | 5.1 | 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. + +