Model Intelligence Sheet
mradermacher/yi-70b-200k-rpmerge-franken-gguf overview
About static quants of https://huggingface.co/DisOOM/Yi-70B-200k-RPMerge-Franken weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-i1-GGUF
Downloads
174
Likes
1
Pipeline
—
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
8 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Yi-70B-200k-RPMerge-Franken.IQ4_XS.gguf | GGUF | IQ4_XS | 35.82 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q2_K.gguf | GGUF | Q2_K | 24.54 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q3_K_L.gguf | GGUF | Q3_K_L | 34.89 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q3_K_M.gguf | GGUF | Q3_K_M | 31.99 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q3_K_S.gguf | GGUF | Q3_K_S | 28.67 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q4_K_M.gguf | GGUF | Q4_K_M | 39.72 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q4_K_S.gguf | GGUF | Q4_K_S | 37.68 GB | Download |
| Yi-70B-200k-RPMerge-Franken.Q5_K_S.gguf | GGUF | Q5_K_S | 45.66 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "DisOOM/Yi-70B-200k-RPMerge-Franken",
"language": [
"en",
"chi"
],
"library_name": "transformers",
"license": "other",
"license_link": "https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE",
"license_name": "yi-license",
"quantized_by": "mradermacher",
"tags": [
"merge",
"mergekit",
"Yi",
"chat",
"conversational"
],
"frontmatter": {
"base_model": "DisOOM/Yi-70B-200k-RPMerge-Franken",
"language": [
"en",
"chi"
],
"library_name": "transformers",
"license": "other",
"license_link": "https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE",
"license_name": "yi-license",
"quantized_by": "mradermacher",
"tags": [
"merge",
"mergekit",
"Yi",
"chat",
"conversational"
]
},
"hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
"summary": "## About static quants of https://huggingface.co/DisOOM/Yi-70B-200k-RPMerge-Franken weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-i1-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: DisOOM/Yi-70B-200k-RPMerge-Franken\nlanguage:\n- en\n- chi\nlibrary_name: transformers\nlicense: other\nlicense_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE\nlicense_name: yi-license\nquantized_by: mradermacher\ntags:\n- merge\n- mergekit\n- Yi\n- chat\n- conversational\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type: -->\n<!-- ### tags: nicoboss -->\nstatic quants of https://huggingface.co/DisOOM/Yi-70B-200k-RPMerge-Franken\n\n<!-- provided-files -->\nweighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-i1-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/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q2_K.gguf) | Q2_K | 26.5 | |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q3_K_S.gguf) | Q3_K_S | 30.9 | |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q3_K_M.gguf) | Q3_K_M | 34.5 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q3_K_L.gguf) | Q3_K_L | 37.6 | |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.IQ4_XS.gguf) | IQ4_XS | 38.6 | |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q4_K_S.gguf) | Q4_K_S | 40.6 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q4_K_M.gguf) | Q4_K_M | 42.7 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q5_K_S.gguf) | Q5_K_S | 49.1 | |\n| [PART 1](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q5_K_M.gguf.part2of2) | Q5_K_M | 50.4 | |\n| [PART 1](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q6_K.gguf.part2of2) | Q6_K | 58.5 | very good quality |\n| [PART 1](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF/resolve/main/Yi-70B-200k-RPMerge-Franken.Q8_0.gguf.part2of2) | Q8_0 | 75.8 | fast, best quality |\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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"merge",
"mergekit",
"Yi",
"chat",
"conversational",
"en",
"chi",
"base_model:DisOOM/Yi-70B-200k-RPMerge-Franken",
"base_model:quantized:DisOOM/Yi-70B-200k-RPMerge-Franken",
"license:other",
"endpoints_compatible",
"region:us"
],
"likes": 1,
"downloads": 174,
"gated": false,
"private": false,
"last_modified": "2024-12-02T03:19:54.000Z",
"created_at": "2024-12-01T06:09:24.000Z",
"pipeline_tag": "",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "674bfd94b8e4df4d0573859b",
"id": "mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF",
"modelId": "mradermacher/Yi-70B-200k-RPMerge-Franken-GGUF",
"sha": "74e7f2751ac52bb2c1beb54744cc702c79717826",
"createdAt": "2024-12-01T06:09:24.000Z",
"lastModified": "2024-12-02T03:19:54.000Z",
"author": "mradermacher",
"downloads": 174,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "transformers",
"siblings_count": 16
}