commit 5d56ce3d365a0ee0a7e52121de97617091306d32 Author: ModelHub XC Date: Tue May 5 13:42:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiniLLM-0.1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..411561b --- /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 +MiniLLM-0.1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiniLLM-0.1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiniLLM-0.1B.IQ4_XS.gguf b/MiniLLM-0.1B.IQ4_XS.gguf new file mode 100644 index 0000000..c45dbee --- /dev/null +++ b/MiniLLM-0.1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4df2892e3932e0ed5a3a969a146993c657b1d8c361ecb76ae04ee55b03da15b +size 71347136 diff --git a/MiniLLM-0.1B.Q2_K.gguf b/MiniLLM-0.1B.Q2_K.gguf new file mode 100644 index 0000000..6afdd9f --- /dev/null +++ b/MiniLLM-0.1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc09d74e2fdd244c0154a04e44b9af2f42c32ac0dbf7b7d0e4c4799089cf9d0 +size 59519936 diff --git a/MiniLLM-0.1B.Q3_K_L.gguf b/MiniLLM-0.1B.Q3_K_L.gguf new file mode 100644 index 0000000..e15cdc3 --- /dev/null +++ b/MiniLLM-0.1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b7ba9ff8439981e9f8d0b1c30756d44d6602d031cc593e3ba62db183e85a67 +size 71009216 diff --git a/MiniLLM-0.1B.Q3_K_M.gguf b/MiniLLM-0.1B.Q3_K_M.gguf new file mode 100644 index 0000000..4d8b103 --- /dev/null +++ b/MiniLLM-0.1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03b7c2c4123e1565994ef35823bead1e8ce89752770fcb843fe6e925f6e69cdb +size 67716032 diff --git a/MiniLLM-0.1B.Q3_K_S.gguf b/MiniLLM-0.1B.Q3_K_S.gguf new file mode 100644 index 0000000..6b5a6a6 --- /dev/null +++ b/MiniLLM-0.1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:992ae35ab9d9aa32c778e7aef5f34622ff09720c165efa18b478ae361200453f +size 63912896 diff --git a/MiniLLM-0.1B.Q4_K_M.gguf b/MiniLLM-0.1B.Q4_K_M.gguf new file mode 100644 index 0000000..8a2e039 --- /dev/null +++ b/MiniLLM-0.1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62f0be0307752eec3aca1107c6b73f8c6a1e349df7cb4dd96527d783ff6dc7d +size 76101056 diff --git a/MiniLLM-0.1B.Q4_K_S.gguf b/MiniLLM-0.1B.Q4_K_S.gguf new file mode 100644 index 0000000..b11bc29 --- /dev/null +++ b/MiniLLM-0.1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef0890bf685c28e1150c4e8d5fd50a0177d9718736d7e0c6da44bf7b225b11c +size 73804736 diff --git a/MiniLLM-0.1B.Q5_K_M.gguf b/MiniLLM-0.1B.Q5_K_M.gguf new file mode 100644 index 0000000..a545078 --- /dev/null +++ b/MiniLLM-0.1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c854dff450c45655b6a27aaf1da3b393b92d1eccd4fab72a0d090aebf92de05 +size 83596736 diff --git a/MiniLLM-0.1B.Q5_K_S.gguf b/MiniLLM-0.1B.Q5_K_S.gguf new file mode 100644 index 0000000..dc8b4ea --- /dev/null +++ b/MiniLLM-0.1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0688961f550bb04a2bfd0b90a6a01d8266b8d99e3648c3daaaf928883bfa677 +size 82160576 diff --git a/MiniLLM-0.1B.Q6_K.gguf b/MiniLLM-0.1B.Q6_K.gguf new file mode 100644 index 0000000..1dfa2f9 --- /dev/null +++ b/MiniLLM-0.1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79171f7163e3ae31c916c4efe9beb02a0bb9156f06f64dd9204d29bba915007e +size 91560896 diff --git a/MiniLLM-0.1B.Q8_0.gguf b/MiniLLM-0.1B.Q8_0.gguf new file mode 100644 index 0000000..a54204a --- /dev/null +++ b/MiniLLM-0.1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d4d01171044e8e12bf91173893646c64ebdfcddee04e503b55f2861b393e65 +size 118050464 diff --git a/MiniLLM-0.1B.f16.gguf b/MiniLLM-0.1B.f16.gguf new file mode 100644 index 0000000..5584bad --- /dev/null +++ b/MiniLLM-0.1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce601195ce0f1fcad92eecb222ed9cb76b99134385c87420febd12e6eb411c73 +size 220590688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e671cc6 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Hippocrene/MiniLLM-0.1B +datasets: +- Skylion007/openwebtext +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- causal-lm +- pretrained +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Hippocrene/MiniLLM-0.1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MiniLLM-0.1B-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/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MiniLLM-0.1B-GGUF/resolve/main/MiniLLM-0.1B.f16.gguf) | f16 | 0.3 | 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. + +