commit 8ad3934f01b060d63a0512c481633d022da03e90 Author: ModelHub XC Date: Mon Sep 28 15:01:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-2-7b-Amharic-pretrained-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c2d97fc --- /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 +llama-2-7b-Amharic-pretrained.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-Amharic-pretrained.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..423f0e9 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: AbelBekele/llama-2-7b-Amharic-pretrained +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AbelBekele/llama-2-7b-Amharic-pretrained + + +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/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-Amharic-pretrained-GGUF/resolve/main/llama-2-7b-Amharic-pretrained.f16.gguf) | f16 | 13.6 | 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. + + diff --git a/llama-2-7b-Amharic-pretrained.IQ4_XS.gguf b/llama-2-7b-Amharic-pretrained.IQ4_XS.gguf new file mode 100644 index 0000000..5f0c3c8 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e245f55cc04938df5a709b34076ea267b6dc27cf30327de18f4e06546a26e138 +size 3647517248 diff --git a/llama-2-7b-Amharic-pretrained.Q2_K.gguf b/llama-2-7b-Amharic-pretrained.Q2_K.gguf new file mode 100644 index 0000000..9af2e7a --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f147b574834daacbed1f403ece9b99403d8883590952ff3d28442c1b5d8f31 +size 2532864576 diff --git a/llama-2-7b-Amharic-pretrained.Q3_K_L.gguf b/llama-2-7b-Amharic-pretrained.Q3_K_L.gguf new file mode 100644 index 0000000..f151cf9 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32079891f3db2bc00e3c58f5152d7fa46d04449567c3f224dae0ffa830435842 +size 3597111872 diff --git a/llama-2-7b-Amharic-pretrained.Q3_K_M.gguf b/llama-2-7b-Amharic-pretrained.Q3_K_M.gguf new file mode 100644 index 0000000..642bc97 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7812f089a7bf55ea405d9ba53c6e7ef5095726c6620c80f4fab8348976d53aba +size 3298005568 diff --git a/llama-2-7b-Amharic-pretrained.Q3_K_S.gguf b/llama-2-7b-Amharic-pretrained.Q3_K_S.gguf new file mode 100644 index 0000000..11f3504 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e604e33980478669d1e088cc1f6a836e3eae51c792f6c16e2e72736a3c3adf +size 2948305472 diff --git a/llama-2-7b-Amharic-pretrained.Q4_K_M.gguf b/llama-2-7b-Amharic-pretrained.Q4_K_M.gguf new file mode 100644 index 0000000..1a55a11 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abf4255433cacedad18ea4d63bc932c53ebcf5a5540d0c10cfd1a5f21295a63 +size 4081005120 diff --git a/llama-2-7b-Amharic-pretrained.Q4_K_S.gguf b/llama-2-7b-Amharic-pretrained.Q4_K_S.gguf new file mode 100644 index 0000000..51df83e --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7806c11120c24f929c2d0ac9e57e97ae04bc1cd00dee404a02bf834858a24b5 +size 3856740928 diff --git a/llama-2-7b-Amharic-pretrained.Q5_K_M.gguf b/llama-2-7b-Amharic-pretrained.Q5_K_M.gguf new file mode 100644 index 0000000..9643111 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b19313f2f950e5b9f54e3410ab6e1898bb318d9417ed14f83dd89973229f118 +size 4783157824 diff --git a/llama-2-7b-Amharic-pretrained.Q5_K_S.gguf b/llama-2-7b-Amharic-pretrained.Q5_K_S.gguf new file mode 100644 index 0000000..4f8e577 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ba4a616c8b00f010df26b194ea74537923b4be80c045056cb2cf51cce865e6 +size 4651692608 diff --git a/llama-2-7b-Amharic-pretrained.Q6_K.gguf b/llama-2-7b-Amharic-pretrained.Q6_K.gguf new file mode 100644 index 0000000..52c7f08 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5397c03da8c7219d0bfb4fef1aa0e889174c64496f8b10920581e4b344bd7154 +size 5529195072 diff --git a/llama-2-7b-Amharic-pretrained.Q8_0.gguf b/llama-2-7b-Amharic-pretrained.Q8_0.gguf new file mode 100644 index 0000000..b252596 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb243d7b3aa55818e44bd99ba1629a454d094f8df52cb4593a26e21533b917f1 +size 7161090624 diff --git a/llama-2-7b-Amharic-pretrained.f16.gguf b/llama-2-7b-Amharic-pretrained.f16.gguf new file mode 100644 index 0000000..0188cd9 --- /dev/null +++ b/llama-2-7b-Amharic-pretrained.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfaab2b8ef0f479bdf6c2f0da08df0c06362d0eebf4fee5fdd73b38469b19785 +size 13478105664