commit 6d4f5f2b311984f62a4907c54da88c14a1c8c5c2 Author: ModelHub XC Date: Mon Jul 6 03:58:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2022317 --- /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 +MobileLLM-1.5B-wikitext2raw-roya.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLM-1.5B-wikitext2raw-roya.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MobileLLM-1.5B-wikitext2raw-roya.IQ4_XS.gguf b/MobileLLM-1.5B-wikitext2raw-roya.IQ4_XS.gguf new file mode 100644 index 0000000..87fe2bc --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1db48b9d65dbe8cbdcf116d9fa4d3325d14264112de1736aa1b40b4e816f265 +size 905759040 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q2_K.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q2_K.gguf new file mode 100644 index 0000000..6182b38 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a78ef37912aaa22fe88449ca462a35830d0191e31b582c8d4ee97b1ef94059 +size 859314240 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_L.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_L.gguf new file mode 100644 index 0000000..b8da26f --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fec6883566b74704b70bea515d9680e67ac5a447d0151b05689588c6ce5bad1b +size 983903040 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_M.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_M.gguf new file mode 100644 index 0000000..d51e49d --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e59830f0590245fede4060cad2d59c7dfddae4f1a8c361596fd01d707fd57d +size 929208640 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_S.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_S.gguf new file mode 100644 index 0000000..ad07400 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:785203bb5eb6a7d12f7bb83822db9723c04e69f9ba0e5ea9b565e64151394b5a +size 855858240 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_M.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_M.gguf new file mode 100644 index 0000000..eabbacf --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c8901084cbf2868a8c6e23fb325535a51755873b600594a6afb0fb15c38535 +size 1099339840 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_S.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_S.gguf new file mode 100644 index 0000000..cc84a93 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2078ee50ecfd239c197f96c69324d9dceaa7bf831698ea2699dab12ab71de31 +size 1053023040 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_M.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_M.gguf new file mode 100644 index 0000000..316a722 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7ae879a4af4e2a2c7e1307176c78285520670cadd169861a545f973627696b +size 1193816640 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_S.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_S.gguf new file mode 100644 index 0000000..17abc5d --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f1168bd9ef327be5c519843ee9d423252a900a6ffda395aff8423049deef2e +size 1165611840 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q6_K.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q6_K.gguf new file mode 100644 index 0000000..4a06bc7 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e10778be14786ab42938b9e610339052672997438c06939bfcebc04bacf46e2 +size 1570239040 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.Q8_0.gguf b/MobileLLM-1.5B-wikitext2raw-roya.Q8_0.gguf new file mode 100644 index 0000000..98587a0 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa082704179b96931e908d1c27467fc2f36df9516b55dbded3b8a52a08edc8c3 +size 1661304640 diff --git a/MobileLLM-1.5B-wikitext2raw-roya.f16.gguf b/MobileLLM-1.5B-wikitext2raw-roya.f16.gguf new file mode 100644 index 0000000..942ffc2 --- /dev/null +++ b/MobileLLM-1.5B-wikitext2raw-roya.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ff78813f702e755cb94f9ecede83c86b4e2be85525e2b9b1afc5f9bf46a1c3 +size 3125880640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6399057 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: mia-llm/MobileLLM-1.5B-wikitext2raw-roya +language: +- en +library_name: transformers +model_name: MobileLLM-1.5B-None.3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/mia-llm/MobileLLM-1.5B-wikitext2raw-roya + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MobileLLM-1.5B-wikitext2raw-roya-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/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MobileLLM-1.5B-wikitext2raw-roya-GGUF/resolve/main/MobileLLM-1.5B-wikitext2raw-roya.f16.gguf) | f16 | 3.2 | 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. + +