Model Intelligence Sheet
mradermacher/olmo-1.7-7b-hf-i1-gguf overview
About weighted/imatrix quants of https://huggingface.co/allenai/OLMo-7B-0424-hf static quants are available at https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-GGUF
Downloads
347
Likes
1
Pipeline
—
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
21 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| OLMo-1.7-7B-hf.i1-IQ1_M.gguf | GGUF | IQ1_M | 1.61 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ1_S.gguf | GGUF | IQ1_S | 1.49 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ2_M.gguf | GGUF | IQ2_M | 2.28 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ2_S.gguf | GGUF | IQ2_S | 2.12 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ2_XS.gguf | GGUF | IQ2_XS | 1.97 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 1.80 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ3_M.gguf | GGUF | IQ3_M | 2.99 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ3_S.gguf | GGUF | IQ3_S | 2.83 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ3_XS.gguf | GGUF | IQ3_XS | 2.69 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 2.49 GB | Download |
| OLMo-1.7-7B-hf.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 3.47 GB | Download |
| OLMo-1.7-7B-hf.i1-Q2_K.gguf | GGUF | Q2_K | 2.44 GB | Download |
| OLMo-1.7-7B-hf.i1-Q3_K_L.gguf | GGUF | Q3_K_L | 3.44 GB | Download |
| OLMo-1.7-7B-hf.i1-Q3_K_M.gguf | GGUF | Q3_K_M | 3.16 GB | Download |
| OLMo-1.7-7B-hf.i1-Q3_K_S.gguf | GGUF | Q3_K_S | 2.83 GB | Download |
| OLMo-1.7-7B-hf.i1-Q4_0.gguf | GGUF | — | 3.67 GB | Download |
| OLMo-1.7-7B-hf.i1-Q4_K_M.gguf | GGUF | Q4_K_M | 3.90 GB | Download |
| OLMo-1.7-7B-hf.i1-Q4_K_S.gguf | GGUF | Q4_K_S | 3.69 GB | Download |
| OLMo-1.7-7B-hf.i1-Q5_K_M.gguf | GGUF | Q5_K_M | 4.56 GB | Download |
| OLMo-1.7-7B-hf.i1-Q5_K_S.gguf | GGUF | Q5_K_S | 4.44 GB | Download |
| OLMo-1.7-7B-hf.i1-Q6_K.gguf | GGUF | Q6_K | 5.26 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "allenai/OLMo-7B-0424-hf",
"datasets": [
"allenai/dolma"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"quantized_by": "mradermacher",
"frontmatter": {
"base_model": "allenai/OLMo-7B-0424-hf",
"datasets": [
"allenai/dolma"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"quantized_by": "mradermacher"
},
"hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
"summary": "## About weighted/imatrix quants of https://huggingface.co/allenai/OLMo-7B-0424-hf static quants are available at https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: allenai/OLMo-7B-0424-hf\ndatasets:\n- allenai/dolma\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\n---\n## About\n\n<!-- ### quantize_version: 1 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: -->\n<!-- ### vocab_type: -->\nweighted/imatrix quants of https://huggingface.co/allenai/OLMo-7B-0424-hf\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.2 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.8 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ3_S.gguf) | i1-IQ3_S | 3.1 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.1 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 3.3 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.8 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.8 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q4_0.gguf) | i1-Q4_0 | 4.0 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.1 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.3 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.9 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.0 | |\n| [GGUF](https://huggingface.co/mradermacher/OLMo-1.7-7B-hf-i1-GGUF/resolve/main/OLMo-1.7-7B-hf.i1-Q6_K.gguf) | i1-Q6_K | 5.8 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time.\n\n<!-- end -->\n",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"en",
"dataset:allenai/dolma",
"base_model:allenai/OLMo-7B-0424-hf",
"base_model:quantized:allenai/OLMo-7B-0424-hf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"likes": 1,
"downloads": 347,
"gated": false,
"private": false,
"last_modified": "2024-12-16T03:20:55.000Z",
"created_at": "2024-04-22T19:44:07.000Z",
"pipeline_tag": "",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6626be07e39da75ea96ff916",
"id": "mradermacher/OLMo-1.7-7B-hf-i1-GGUF",
"modelId": "mradermacher/OLMo-1.7-7B-hf-i1-GGUF",
"sha": "4172e86baaa7ebce66df3286ea48f8093a6ec23c",
"createdAt": "2024-04-22T19:44:07.000Z",
"lastModified": "2024-12-16T03:20:55.000Z",
"author": "mradermacher",
"downloads": 347,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "transformers",
"siblings_count": 24
}