commit d5f7360c1303fdc4d64c122f7a8ec79f0bc6ce3c Author: ModelHub XC Date: Sun May 31 02:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7B-mono-Hausa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c587379 --- /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-mono-Hausa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-mono-Hausa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7B-mono-Hausa.IQ4_XS.gguf b/Llama-2-7B-mono-Hausa.IQ4_XS.gguf new file mode 100644 index 0000000..3e87e8a --- /dev/null +++ b/Llama-2-7B-mono-Hausa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6db84cef8a03e06459524d29d0c22ba01be6310ec4658239fb4f90ccdb126e +size 3647517408 diff --git a/Llama-2-7B-mono-Hausa.Q2_K.gguf b/Llama-2-7B-mono-Hausa.Q2_K.gguf new file mode 100644 index 0000000..2fa44a8 --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdcf37c046a574925d7f99259175a5cc6e056f3f0524754fca11f6e76ad475a5 +size 2532864736 diff --git a/Llama-2-7B-mono-Hausa.Q3_K_L.gguf b/Llama-2-7B-mono-Hausa.Q3_K_L.gguf new file mode 100644 index 0000000..74752fa --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0fc172938c7ee658d41cc087ffe6eb5222fd7a64a7cd9bceb0f6b0d44cb8db +size 3597112032 diff --git a/Llama-2-7B-mono-Hausa.Q3_K_M.gguf b/Llama-2-7B-mono-Hausa.Q3_K_M.gguf new file mode 100644 index 0000000..7db82e8 --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0953c4aecce2307d6b84a180ba8c7eec8d0c5d02272e5beeb169fbb42cbe1f80 +size 3298005728 diff --git a/Llama-2-7B-mono-Hausa.Q3_K_S.gguf b/Llama-2-7B-mono-Hausa.Q3_K_S.gguf new file mode 100644 index 0000000..7da9409 --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2e7eba4b972b21ee8fbb8a8c88b4f9acca19178f0e4c8500ab300af6023a1a +size 2948305632 diff --git a/Llama-2-7B-mono-Hausa.Q4_K_M.gguf b/Llama-2-7B-mono-Hausa.Q4_K_M.gguf new file mode 100644 index 0000000..8b5c5e5 --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa497d415601aef75550f6294dc9dc918a8d9a827d7410df5b02c08f437a12f0 +size 4081005280 diff --git a/Llama-2-7B-mono-Hausa.Q4_K_S.gguf b/Llama-2-7B-mono-Hausa.Q4_K_S.gguf new file mode 100644 index 0000000..6f6eadf --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff31c6701356fa3fb1dd7debcd13277bbb490e447c4155b03085084dfc9144df +size 3856741088 diff --git a/Llama-2-7B-mono-Hausa.Q5_K_M.gguf b/Llama-2-7B-mono-Hausa.Q5_K_M.gguf new file mode 100644 index 0000000..74867fb --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c834db05b7d3533601b119790ee3622aec67146f4f6f013a09600c14fdb45a69 +size 4783157984 diff --git a/Llama-2-7B-mono-Hausa.Q5_K_S.gguf b/Llama-2-7B-mono-Hausa.Q5_K_S.gguf new file mode 100644 index 0000000..278e644 --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b5235bc0c63033ccff90306ea1473b5b9c4ae6d4c773bb284a1bae5a3e87b1 +size 4651692768 diff --git a/Llama-2-7B-mono-Hausa.Q6_K.gguf b/Llama-2-7B-mono-Hausa.Q6_K.gguf new file mode 100644 index 0000000..2f1b34f --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e730f986c0535a63ece374175587aac7d6c01ec3296c16b053d331a383f6f90 +size 5529195232 diff --git a/Llama-2-7B-mono-Hausa.Q8_0.gguf b/Llama-2-7B-mono-Hausa.Q8_0.gguf new file mode 100644 index 0000000..ae9356c --- /dev/null +++ b/Llama-2-7B-mono-Hausa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f9e57e8531971f061fdd14f24fb90f664c9d02fdbfaeedc26779e3c7a51b6c +size 7161090784 diff --git a/Llama-2-7B-mono-Hausa.f16.gguf b/Llama-2-7B-mono-Hausa.f16.gguf new file mode 100644 index 0000000..3b89f5f --- /dev/null +++ b/Llama-2-7B-mono-Hausa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5c992140e176dfc0dc9014e32fa4129f946006050dca2ca3e2b17067242fb0 +size 13478105824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..edb5984 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: almanach/Llama-2-7B-mono-Hausa +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/almanach/Llama-2-7B-mono-Hausa + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7B-mono-Hausa-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/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-mono-Hausa-GGUF/resolve/main/Llama-2-7B-mono-Hausa.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. + +