commit b88ccfc97e7dc6a3ebed07cf67dd662bf9d00bb5 Author: ModelHub XC Date: Tue Sep 15 15:30:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SomaliLM-150M-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60c33e6 --- /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 +SomaliLM-150M-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SomaliLM-150M-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9681853 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: yacdev/SomaliLM-150M-Instruct +datasets: +- yacdev/somali-100k-native-conversations +language: +- so +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- somali +- causal-lm +- sft +- conversational +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yacdev/SomaliLM-150M-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SomaliLM-150M-Instruct-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/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SomaliLM-150M-Instruct-GGUF/resolve/main/SomaliLM-150M-Instruct.f16.gguf) | f16 | 0.4 | 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/SomaliLM-150M-Instruct.IQ4_XS.gguf b/SomaliLM-150M-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b0585a0 --- /dev/null +++ b/SomaliLM-150M-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950194264ea14985c53ba0a9cb0db40e624ecc89a27aa0c27e18b5da9c81d835 +size 86787584 diff --git a/SomaliLM-150M-Instruct.Q2_K.gguf b/SomaliLM-150M-Instruct.Q2_K.gguf new file mode 100644 index 0000000..10551ec --- /dev/null +++ b/SomaliLM-150M-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe871415ecf39f6c54a5eebb370004b8902556902cb5a96412cf9e6163ff786 +size 65885696 diff --git a/SomaliLM-150M-Instruct.Q3_K_L.gguf b/SomaliLM-150M-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e5f5be2 --- /dev/null +++ b/SomaliLM-150M-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb1f0aa9837e4c95201513043bad998e6d20de6723a82dd0b3e1413738a0079 +size 85472768 diff --git a/SomaliLM-150M-Instruct.Q3_K_M.gguf b/SomaliLM-150M-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ea0295d --- /dev/null +++ b/SomaliLM-150M-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9660fe597f4f6709f7cdd6ec3ee2e267fc5019e41e1efe0a81675783d3432b73 +size 80090624 diff --git a/SomaliLM-150M-Instruct.Q3_K_S.gguf b/SomaliLM-150M-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..d98018c --- /dev/null +++ b/SomaliLM-150M-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2cd397c403c66325c2e4dc0a54215fddc24fee55be6e087a4d22eb1f4b910b +size 73713152 diff --git a/SomaliLM-150M-Instruct.Q4_K_M.gguf b/SomaliLM-150M-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..6f8083c --- /dev/null +++ b/SomaliLM-150M-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a554b4540f7943d5312ce644162515022e4a9be9a32c10e12e5a614db319bdca +size 94670336 diff --git a/SomaliLM-150M-Instruct.Q4_K_S.gguf b/SomaliLM-150M-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..ec5db3a --- /dev/null +++ b/SomaliLM-150M-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f1f91406d6a5d89aac10c93c93f0d52dc3d6410ec861aa1027e97ba40df66d +size 90646016 diff --git a/SomaliLM-150M-Instruct.Q5_K_M.gguf b/SomaliLM-150M-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..f36a8d9 --- /dev/null +++ b/SomaliLM-150M-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c830cafd242d7f08ba168d16d43f85424195805dd8b453f01f57ec42aaeca4e +size 107744768 diff --git a/SomaliLM-150M-Instruct.Q5_K_S.gguf b/SomaliLM-150M-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..cf213ca --- /dev/null +++ b/SomaliLM-150M-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906b444ec08000c417356428c92b6aea3a20a531255511a04b45198b135b976a +size 105342464 diff --git a/SomaliLM-150M-Instruct.Q6_K.gguf b/SomaliLM-150M-Instruct.Q6_K.gguf new file mode 100644 index 0000000..5ee94be --- /dev/null +++ b/SomaliLM-150M-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b94da61798fc741ee6f526d896bb594be8a4026770d975ceec99965a5cc19d +size 121636352 diff --git a/SomaliLM-150M-Instruct.Q8_0.gguf b/SomaliLM-150M-Instruct.Q8_0.gguf new file mode 100644 index 0000000..67070ff --- /dev/null +++ b/SomaliLM-150M-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fad63c79d29485b2b5d643e0f3fb0a97f4b49a8a30ab0125584b5dce1d11762 +size 157301088 diff --git a/SomaliLM-150M-Instruct.f16.gguf b/SomaliLM-150M-Instruct.f16.gguf new file mode 100644 index 0000000..4ac36ea --- /dev/null +++ b/SomaliLM-150M-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c51be55f7a42a89a3fec2704264199f15765d458fcbc2c3307b1dec463b563d +size 295358208