commit 5cbb442a09f9d2db81f06ccc4badd1ce687e00de Author: ModelHub XC Date: Thu Oct 8 13:41:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/swahili-Instruct-llama-2-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a05fa0d --- /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 +swahili-Instruct-llama-2-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +swahili-Instruct-llama-2-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f71b69b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Mollel/swahili-Instruct-llama-2-7b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama-2 +- trl +- lora +--- +## About + + + + + + +static quants of https://huggingface.co/Mollel/swahili-Instruct-llama-2-7b + + +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/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/swahili-Instruct-llama-2-7b-GGUF/resolve/main/swahili-Instruct-llama-2-7b.f16.gguf) | f16 | 13.9 | 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/swahili-Instruct-llama-2-7b.IQ4_XS.gguf b/swahili-Instruct-llama-2-7b.IQ4_XS.gguf new file mode 100644 index 0000000..270e931 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f54cd16e302a98c12eeb8614d620908560d5741380f5a1c65fc0b7abdee82c +size 3742338176 diff --git a/swahili-Instruct-llama-2-7b.Q2_K.gguf b/swahili-Instruct-llama-2-7b.Q2_K.gguf new file mode 100644 index 0000000..7262980 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df128cf9a63e71479117108f224a5f0ed08ec9925e8a6d8091e10ce3a01b1689 +size 2613497408 diff --git a/swahili-Instruct-llama-2-7b.Q3_K_L.gguf b/swahili-Instruct-llama-2-7b.Q3_K_L.gguf new file mode 100644 index 0000000..548bae3 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53e686caf5eea2249f589d826c34582ed0c1a0e76ae9d9ccd633cda931e1f75 +size 3684838752 diff --git a/swahili-Instruct-llama-2-7b.Q3_K_M.gguf b/swahili-Instruct-llama-2-7b.Q3_K_M.gguf new file mode 100644 index 0000000..e5655fc --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99d42ff793eb773a038f9bd4f552dfd6d35842cb402e9640889bcc87d2d974c +size 3385732448 diff --git a/swahili-Instruct-llama-2-7b.Q3_K_S.gguf b/swahili-Instruct-llama-2-7b.Q3_K_S.gguf new file mode 100644 index 0000000..988faf2 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec86923beb87043e7c51dd178c0616883501436a68d8546f5b5aa9c7ecbbbe07 +size 3036032352 diff --git a/swahili-Instruct-llama-2-7b.Q4_K_M.gguf b/swahili-Instruct-llama-2-7b.Q4_K_M.gguf new file mode 100644 index 0000000..717e415 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bfce9bf9342e96b57943666467f883b0d819f2189c06444023641a3a1dc7a6 +size 4178008832 diff --git a/swahili-Instruct-llama-2-7b.Q4_K_S.gguf b/swahili-Instruct-llama-2-7b.Q4_K_S.gguf new file mode 100644 index 0000000..2c03bbf --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9833fb266a043a4effc4f54511d6cd3497f68fc2b389751045b4be222e8e0bb +size 3953744640 diff --git a/swahili-Instruct-llama-2-7b.Q5_K_M.gguf b/swahili-Instruct-llama-2-7b.Q5_K_M.gguf new file mode 100644 index 0000000..fa296a7 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3ea35735f4d58fa6b95fbf8a79fddf20e629c964d4b73b50bca0bdde8d1a9d +size 4888892672 diff --git a/swahili-Instruct-llama-2-7b.Q5_K_S.gguf b/swahili-Instruct-llama-2-7b.Q5_K_S.gguf new file mode 100644 index 0000000..dc9fcad --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36230d211dc0282ac93c7de7f0eca33748773b8f08e34042dab9c7dcbbad0bcd +size 4757427456 diff --git a/swahili-Instruct-llama-2-7b.Q6_K.gguf b/swahili-Instruct-llama-2-7b.Q6_K.gguf new file mode 100644 index 0000000..902f852 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be05ca0be3f0716bd204500d1788f6fbf14269b94670c0f2a7e2345cf9d39437 +size 5644206752 diff --git a/swahili-Instruct-llama-2-7b.Q8_0.gguf b/swahili-Instruct-llama-2-7b.Q8_0.gguf new file mode 100644 index 0000000..8bb23eb --- /dev/null +++ b/swahili-Instruct-llama-2-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4a2a3697d211e1c85b0d813c6ad5bc8b4ab3cab1c3b0c7529091474279226a +size 7309935456 diff --git a/swahili-Instruct-llama-2-7b.f16.gguf b/swahili-Instruct-llama-2-7b.f16.gguf new file mode 100644 index 0000000..93483e7 --- /dev/null +++ b/swahili-Instruct-llama-2-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362ad654bde0d9b2c6450d45ffd108605f3a05b389f602486f31576219ca157c +size 13757917536