commit 0d8ef6f5814093bd54182c31dd95ca7205006d05 Author: ModelHub XC Date: Fri Oct 30 14:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-7B-0724-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c2c8cc0 --- /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 +OLMo-7B-0724-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0724-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-7B-0724-hf.IQ4_XS.gguf b/OLMo-7B-0724-hf.IQ4_XS.gguf new file mode 100644 index 0000000..cffc329 --- /dev/null +++ b/OLMo-7B-0724-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7021fd559f54894b2f6b228fe66237551e651d44c729f884c11633e401ac92bd +size 3748824832 diff --git a/OLMo-7B-0724-hf.Q2_K.gguf b/OLMo-7B-0724-hf.Q2_K.gguf new file mode 100644 index 0000000..eecd7f3 --- /dev/null +++ b/OLMo-7B-0724-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4579b377b382cd7770741ca97cf1d3a8be9544089ed447a1e8b2bd4e5adb14b +size 2618943232 diff --git a/OLMo-7B-0724-hf.Q3_K_L.gguf b/OLMo-7B-0724-hf.Q3_K_L.gguf new file mode 100644 index 0000000..ce583a9 --- /dev/null +++ b/OLMo-7B-0724-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076fb693463a2929683d9cb0f690faae3c2e8ced61e21c0f2eb4e19517a351b7 +size 3690804992 diff --git a/OLMo-7B-0724-hf.Q3_K_M.gguf b/OLMo-7B-0724-hf.Q3_K_M.gguf new file mode 100644 index 0000000..b1f006c --- /dev/null +++ b/OLMo-7B-0724-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:727189a63627502f785c9751f1769c38756e3c7e7f4129ebc60650bde3fa1f1f +size 3391698688 diff --git a/OLMo-7B-0724-hf.Q3_K_S.gguf b/OLMo-7B-0724-hf.Q3_K_S.gguf new file mode 100644 index 0000000..f9a628f --- /dev/null +++ b/OLMo-7B-0724-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7354ddbd7727bee09f757d2663246158f9a057041ea90e6f006c1facc2a69bbd +size 3041998592 diff --git a/OLMo-7B-0724-hf.Q4_K_M.gguf b/OLMo-7B-0724-hf.Q4_K_M.gguf new file mode 100644 index 0000000..173fee7 --- /dev/null +++ b/OLMo-7B-0724-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ddb56a216f1584319b6f326c1c6bfd0b6fa2c54577e9000808dbada3e0e611 +size 4184655616 diff --git a/OLMo-7B-0724-hf.Q4_K_S.gguf b/OLMo-7B-0724-hf.Q4_K_S.gguf new file mode 100644 index 0000000..1476c59 --- /dev/null +++ b/OLMo-7B-0724-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafd99c549ecaa581a89a4e2fc0a0cd41aa46ef0603caaef848d9533002cc0dc +size 3960391424 diff --git a/OLMo-7B-0724-hf.Q5_K_M.gguf b/OLMo-7B-0724-hf.Q5_K_M.gguf new file mode 100644 index 0000000..a4adcee --- /dev/null +++ b/OLMo-7B-0724-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36560347b4ffd592e8b5ccc7fa2fa96af9eb3f9e69a091d75394c4bf9a1b4ccd +size 4896179968 diff --git a/OLMo-7B-0724-hf.Q5_K_S.gguf b/OLMo-7B-0724-hf.Q5_K_S.gguf new file mode 100644 index 0000000..fc9fb57 --- /dev/null +++ b/OLMo-7B-0724-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933058652c99f6931d057ef6780e5806e32207cc8779b1c7ea03ba6b8b3346b8 +size 4764714752 diff --git a/OLMo-7B-0724-hf.Q6_K.gguf b/OLMo-7B-0724-hf.Q6_K.gguf new file mode 100644 index 0000000..2e72153 --- /dev/null +++ b/OLMo-7B-0724-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a9fde3c595988bdf230eed9725c49fefdc123a0f8c7a56693dfee9ca16f39c +size 5652174592 diff --git a/OLMo-7B-0724-hf.Q8_0.gguf b/OLMo-7B-0724-hf.Q8_0.gguf new file mode 100644 index 0000000..e5f63ef --- /dev/null +++ b/OLMo-7B-0724-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94ab7ee677111a62667cb1e6f2c61e1251b80cfb837e696396f659e74ad32b8 +size 7320385280 diff --git a/OLMo-7B-0724-hf.f16.gguf b/OLMo-7B-0724-hf.f16.gguf new file mode 100644 index 0000000..e86f6e1 --- /dev/null +++ b/OLMo-7B-0724-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b58dac59aedb07dc33e824b4731f11ca1f7c2f22b343f85444096ecad8de44 +size 13777975040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f338534 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: allenai/OLMo-7B-0724-hf +datasets: +- allenai/dolma +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allenai/OLMo-7B-0724-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OLMo-7B-0724-hf-i1-GGUF +## 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/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0724-hf-GGUF/resolve/main/OLMo-7B-0724-hf.f16.gguf) | f16 | 13.9 | 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. + +