commit abb527cf7e5fdcb410ddae7cbcdc957cd1c165b4 Author: ModelHub XC Date: Sun Apr 12 12:29:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/fineweb-latent-0.5B-10B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bb5f56 --- /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 +fineweb-latent-0.5B-10B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +fineweb-latent-0.5B-10B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2fd1fd0 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: snoop2head/fineweb-latent-0.5B-10B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/snoop2head/fineweb-latent-0.5B-10B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#fineweb-latent-0.5B-10B-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/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/fineweb-latent-0.5B-10B-GGUF/resolve/main/fineweb-latent-0.5B-10B.f16.gguf) | f16 | 0.8 | 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/fineweb-latent-0.5B-10B.IQ4_XS.gguf b/fineweb-latent-0.5B-10B.IQ4_XS.gguf new file mode 100644 index 0000000..e28da9d --- /dev/null +++ b/fineweb-latent-0.5B-10B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d4cd4d2e01a72b2269deb27253b6817e1e3c94b01f65a44a5342fa43c74e28 +size 210379776 diff --git a/fineweb-latent-0.5B-10B.Q2_K.gguf b/fineweb-latent-0.5B-10B.Q2_K.gguf new file mode 100644 index 0000000..508a3e7 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97901cc312ea5329eb1e1d03d290e1b8a85061161c96b16546edaae86b021650 +size 151892992 diff --git a/fineweb-latent-0.5B-10B.Q3_K_L.gguf b/fineweb-latent-0.5B-10B.Q3_K_L.gguf new file mode 100644 index 0000000..f8dfa88 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e240a081e635d58fb7afdf0bcab77ab99a0b0929f061d1a774bdf93a6efed42 +size 205208576 diff --git a/fineweb-latent-0.5B-10B.Q3_K_M.gguf b/fineweb-latent-0.5B-10B.Q3_K_M.gguf new file mode 100644 index 0000000..6b56a18 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc2027e2c30097775cd382a188e545ec76ec23aa37d4356346092b69a3bb0b6 +size 190888960 diff --git a/fineweb-latent-0.5B-10B.Q3_K_S.gguf b/fineweb-latent-0.5B-10B.Q3_K_S.gguf new file mode 100644 index 0000000..5376831 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f678db41fe2d51b0426d5704ff9cbc11fe04e8fb56a86d8014bff6066cdb77d8 +size 174390272 diff --git a/fineweb-latent-0.5B-10B.Q4_K_M.gguf b/fineweb-latent-0.5B-10B.Q4_K_M.gguf new file mode 100644 index 0000000..13d245e --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd837d90712d6321ec58d7f66c584b51be7125f5b9ece57f9aea6a46aa5f6207 +size 231851008 diff --git a/fineweb-latent-0.5B-10B.Q4_K_S.gguf b/fineweb-latent-0.5B-10B.Q4_K_S.gguf new file mode 100644 index 0000000..b83e863 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ee5b253a959f96bf0e4e0f9863cf1eaee407cbe33c066af1c175228eb4b672 +size 221291520 diff --git a/fineweb-latent-0.5B-10B.Q5_K_M.gguf b/fineweb-latent-0.5B-10B.Q5_K_M.gguf new file mode 100644 index 0000000..9858938 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2d76608c405d2e485b67dbdfd45b6e19bb31933dd0279b0e54ab87a071cc25 +size 268583936 diff --git a/fineweb-latent-0.5B-10B.Q5_K_S.gguf b/fineweb-latent-0.5B-10B.Q5_K_S.gguf new file mode 100644 index 0000000..e8271fc --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3ddca559098126df73b4b25e843517a99b840f7b121988272e34c2fea23a0c +size 262317056 diff --git a/fineweb-latent-0.5B-10B.Q6_K.gguf b/fineweb-latent-0.5B-10B.Q6_K.gguf new file mode 100644 index 0000000..35fc839 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7056334606c829809a074b88c01e21d6068d48f07b080c2530e7ebffc04fec +size 307612672 diff --git a/fineweb-latent-0.5B-10B.Q8_0.gguf b/fineweb-latent-0.5B-10B.Q8_0.gguf new file mode 100644 index 0000000..ff56e40 --- /dev/null +++ b/fineweb-latent-0.5B-10B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a9d3127ea8a5db44d8e1954abbd68db776b34fe980ef3e2f5bcd18b3133b6d +size 398146560 diff --git a/fineweb-latent-0.5B-10B.f16.gguf b/fineweb-latent-0.5B-10B.f16.gguf new file mode 100644 index 0000000..8b7ae5f --- /dev/null +++ b/fineweb-latent-0.5B-10B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b5eccb8736211077ab191b7285b950c2f6c5b1042dadd6d89041421eabb646 +size 748600320