commit d1e1400cfb68a4923d47415b08692969eb7efb28 Author: ModelHub XC Date: Mon Jul 20 12:41:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-7B-0424-Instruct-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c7992b --- /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-0424-Instruct-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-7B-0424-Instruct-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-7B-0424-Instruct-hf.IQ4_XS.gguf b/OLMo-7B-0424-Instruct-hf.IQ4_XS.gguf new file mode 100644 index 0000000..178a250 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df0beed5917c4ab30a747549dc374b946f4d9c2b167d8913e9029fb73e63762 +size 3748825760 diff --git a/OLMo-7B-0424-Instruct-hf.Q2_K.gguf b/OLMo-7B-0424-Instruct-hf.Q2_K.gguf new file mode 100644 index 0000000..6c07b40 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11af521ffd93dcccbf4911195183dfcb47931ace34e16d7cd02329d66cb1a5d +size 2618944160 diff --git a/OLMo-7B-0424-Instruct-hf.Q3_K_L.gguf b/OLMo-7B-0424-Instruct-hf.Q3_K_L.gguf new file mode 100644 index 0000000..77f774c --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e40e78ce1d60e0f7408411ca48b20397354a6a25599f9500ad32556da01d82 +size 3690805920 diff --git a/OLMo-7B-0424-Instruct-hf.Q3_K_M.gguf b/OLMo-7B-0424-Instruct-hf.Q3_K_M.gguf new file mode 100644 index 0000000..5ae0941 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5787e3d45b2cd21901a88c5b11e9aa019e6dd858adb86a439a008b4df80dc0e7 +size 3391699616 diff --git a/OLMo-7B-0424-Instruct-hf.Q3_K_S.gguf b/OLMo-7B-0424-Instruct-hf.Q3_K_S.gguf new file mode 100644 index 0000000..c99fa53 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f04d71bce07f8d451ac228277127c9522146cfbe8b41a74447607741a99632 +size 3041999520 diff --git a/OLMo-7B-0424-Instruct-hf.Q4_K_M.gguf b/OLMo-7B-0424-Instruct-hf.Q4_K_M.gguf new file mode 100644 index 0000000..9489880 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2919bc0b1d46e5d95707ba9fb0548c5443e530cc01391a23b8ac07aaaef9291 +size 4184656544 diff --git a/OLMo-7B-0424-Instruct-hf.Q4_K_S.gguf b/OLMo-7B-0424-Instruct-hf.Q4_K_S.gguf new file mode 100644 index 0000000..30438c5 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0526d8c6f0354a15363e4f4454e8023242b121d8f1dc0dee48227529b3c83a0d +size 3960392352 diff --git a/OLMo-7B-0424-Instruct-hf.Q5_K_M.gguf b/OLMo-7B-0424-Instruct-hf.Q5_K_M.gguf new file mode 100644 index 0000000..71f1f23 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557ba3007ac82fedb96887a605b868576ab5c429c7fa7e9871374bf21f304dce +size 4896180896 diff --git a/OLMo-7B-0424-Instruct-hf.Q5_K_S.gguf b/OLMo-7B-0424-Instruct-hf.Q5_K_S.gguf new file mode 100644 index 0000000..511496d --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc81b3cebad171b74acd58bd5106d88fdb012482db7ca6a18c66a3dba895a56 +size 4764715680 diff --git a/OLMo-7B-0424-Instruct-hf.Q6_K.gguf b/OLMo-7B-0424-Instruct-hf.Q6_K.gguf new file mode 100644 index 0000000..4884553 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc048bd4895cd6db070b888102e82eca32e26d7f88314c562ce3b9942575ea0 +size 5652175520 diff --git a/OLMo-7B-0424-Instruct-hf.Q8_0.gguf b/OLMo-7B-0424-Instruct-hf.Q8_0.gguf new file mode 100644 index 0000000..08c87d8 --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8c62cc8388404708340fa3c9efe03dcfe137c6904d48a81b4b2e70865ad985 +size 7320386208 diff --git a/OLMo-7B-0424-Instruct-hf.f16.gguf b/OLMo-7B-0424-Instruct-hf.f16.gguf new file mode 100644 index 0000000..e941d3a --- /dev/null +++ b/OLMo-7B-0424-Instruct-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7315090a21c72b6c653e05c667b70681724b2c94b84e3a7856b432ea89a25bbf +size 13777975968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e48f19 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: allenai/OLMo-7B-0424-Instruct-hf +datasets: +- allenai/dolma +- allenai/tulu-v2-sft-mixture-olmo-4096 +- allenai/ultrafeedback_binarized_cleaned +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allenai/OLMo-7B-0424-Instruct-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-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-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-hf.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-7B-0424-Instruct-hf-GGUF/resolve/main/OLMo-7B-0424-Instruct-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. + +