commit ff305aaa59b5c518fcea5d32b5c73cbef225faee Author: ModelHub XC Date: Fri Oct 2 15:57:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f4ea4da --- /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 +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.f16.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..24b6097 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: mlfoundations-dev/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/mlfoundations-dev/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-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/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr-GGUF/resolve/main/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.f16.gguf) | f16 | 14.6 | 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/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_XS.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_XS.gguf new file mode 100644 index 0000000..86c8733 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74dfd00db995188ff146b1e4a5c02e5cce9e95c0fc35307e9780eaa7d7ff36f2 +size 3948664192 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q2_K.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q2_K.gguf new file mode 100644 index 0000000..5e14796 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffaf7485cb34f9614d280ab35b356ea4eb8cb2ee231440939b664bb486ae8e5 +size 2722878848 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_L.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_L.gguf new file mode 100644 index 0000000..2d43fb0 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7afd2be9d19aae293ec9d9050d7aa64a622b5e50d5d3fc1f0f293dbe583b8a +size 3825980800 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_M.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_M.gguf new file mode 100644 index 0000000..860c59c --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c920f36879a3b212ffa7ad61aaec6d6c55ec25fd87cef3da27c3cb34cc12a9c6 +size 3522942336 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_S.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_S.gguf new file mode 100644 index 0000000..1b8b6a1 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce9952297764c2ae940331daf5e7b87209e0b68621fb322fecd927fa0a666fc +size 3168523648 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_M.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_M.gguf new file mode 100644 index 0000000..5bfaca7 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe94e3dd5355b34c9387907c029c5697b11055a72377491a69339c42a04ba7e +size 4372813184 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_S.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_S.gguf new file mode 100644 index 0000000..3491eb9 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5799bdbe01857bd9c6d1cf4c667a44599b4b68a315b79dae4791141d8a88fee8 +size 4144747904 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_M.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_M.gguf new file mode 100644 index 0000000..a797358 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cfca6f4c059e63d06f3df75e70a354237d0063f197f18dfee9e4e2383a35add +size 5136176512 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_S.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_S.gguf new file mode 100644 index 0000000..83dac43 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53c7e1d2e2d837174b08e36b557520f295f8bb03e1f51153ec511da18a600a3 +size 5002483072 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q6_K.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q6_K.gguf new file mode 100644 index 0000000..f032020 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f623476120d305c67aa4b333160150f21aa6cb0daa772ec66b4d4b01ebb2e1 +size 5947250048 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q8_0.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q8_0.gguf new file mode 100644 index 0000000..798fa58 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f5539b7c66a447c7e450d57b3083ed5dbec6e5ec8510d1a1002c0670046c1f +size 7702566272 diff --git a/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.f16.gguf b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.f16.gguf new file mode 100644 index 0000000..924a825 --- /dev/null +++ b/oh-mistral-bs512_lr2_00E-06_schedulerconstant_warmup5_00E-02_minlr.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c566d25df066e8b4b5513f50314a16d618554032773b75bb9aa19bb8878caa4 +size 14497338752