commit 1d0efcbc6cd23cc673b479925a0d1c465f64cfa1 Author: ModelHub XC Date: Sun Jun 21 14:28:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Olmo-1b-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..80dedfa --- /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-1b-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-1b-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Olmo-1b-Instruct.IQ4_XS.gguf b/Olmo-1b-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..48b63bb --- /dev/null +++ b/Olmo-1b-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eafbd1fdc744fd8f11f7ad87e0aaae400565e9324b8ef7aa18d94cbcf768feac +size 857526880 diff --git a/Olmo-1b-Instruct.Q2_K.gguf b/Olmo-1b-Instruct.Q2_K.gguf new file mode 100644 index 0000000..b313001 --- /dev/null +++ b/Olmo-1b-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744656a7511e51e153972e65531ddf937288bd87a465ef9ba2904a2128834fa7 +size 633328224 diff --git a/Olmo-1b-Instruct.Q3_K_L.gguf b/Olmo-1b-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..91efb10 --- /dev/null +++ b/Olmo-1b-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e8c88914ed5c6b6d399012c79be673bbd51d65af95fec3f011b26bf04d644c +size 826167904 diff --git a/Olmo-1b-Instruct.Q3_K_M.gguf b/Olmo-1b-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ed1cb37 --- /dev/null +++ b/Olmo-1b-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca8983bd9334451430fc6428d1ee5be6ac8ac4392b64eb9ece7bbcd112a4cf5e +size 778981984 diff --git a/Olmo-1b-Instruct.Q3_K_S.gguf b/Olmo-1b-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..df003bf --- /dev/null +++ b/Olmo-1b-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862148ec331473e9667f7618f2cac4cf0e55768ca0e9960077d52389bb7358f9 +size 722358880 diff --git a/Olmo-1b-Instruct.Q4_K_M.gguf b/Olmo-1b-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f365eaa --- /dev/null +++ b/Olmo-1b-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835f7fc8eebdd49d3c97625c775df943b476c500c48e9d064baf745fa9a61a36 +size 935514720 diff --git a/Olmo-1b-Instruct.Q4_K_S.gguf b/Olmo-1b-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..4c2dd34 --- /dev/null +++ b/Olmo-1b-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b7da6c759f74b88749f1e54dfd01518e5f42e2597385f01f2e2bd243a1e637 +size 898552416 diff --git a/Olmo-1b-Instruct.Q5_K_M.gguf b/Olmo-1b-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..922ab7d --- /dev/null +++ b/Olmo-1b-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fd341d8eede140b0a03d6896e7226280891093719309d437e8c3f7b27d8e18 +size 1074451040 diff --git a/Olmo-1b-Instruct.Q5_K_S.gguf b/Olmo-1b-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..73da2c2 --- /dev/null +++ b/Olmo-1b-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e562e7788ebdd6b551f5f83197da2d8f02dc87dfccb9f24224f97980347de2e7 +size 1052168800 diff --git a/Olmo-1b-Instruct.Q6_K.gguf b/Olmo-1b-Instruct.Q6_K.gguf new file mode 100644 index 0000000..67e28de --- /dev/null +++ b/Olmo-1b-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbad31537809ca8d4a8120fd078e02aa91afe0b32fa8d94d5b5355ef01517915 +size 1222070880 diff --git a/Olmo-1b-Instruct.Q8_0.gguf b/Olmo-1b-Instruct.Q8_0.gguf new file mode 100644 index 0000000..5a65466 --- /dev/null +++ b/Olmo-1b-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f480311acc04b35363ae03e4d384ce0ffd5fd1c7209444a168af16dcf91f12 +size 1581666912 diff --git a/Olmo-1b-Instruct.f16.gguf b/Olmo-1b-Instruct.f16.gguf new file mode 100644 index 0000000..df5f7a3 --- /dev/null +++ b/Olmo-1b-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2712126e0ffb75573933d4ef0b24e75c04f6f72b72519573778408ff2cefc14 +size 2973651552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..900a91e --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Codemaster67/Olmo-1b-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Codemaster67/Olmo-1b-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Olmo-1b-Instruct-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/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-1b-Instruct-GGUF/resolve/main/Olmo-1b-Instruct.f16.gguf) | f16 | 3.1 | 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. + +