afrideva/lmcocktail-phi-2-v1-gguf Q5_K_M GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
afrideva/lmcocktail-phi-2-v1-gguf overview
This is a 50%-50% model of the phi2 alpca gpt4 and phi2 ultrachat200K models. https://huggingface.co/Yhyu13/phi-2-sft-alpacagpt4en-ep1 https://huggingface.co/venkycs/phi-2-ultrachat200k # Code The LM-cocktail is novel technique for merging multiple models https://arxiv.org/abs/2311.13534 Code is backed up by this repo https://github.com/FlagOpen/FlagEmbedding.git Merging scripts available under the ./scripts folder
Downloads
91
Likes
0
Pipeline
text-generation
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
7 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| lmcocktail-phi-2-v1.fp16.gguf | GGUF | — | 5.18 GB | Download |
| lmcocktail-phi-2-v1.q2_k.gguf | GGUF | Q2_K | 1.09 GB | Download |
| lmcocktail-phi-2-v1.q3_k_m.gguf | GGUF | Q3_K_M | 1.38 GB | Download |
| lmcocktail-phi-2-v1.q4_k_m.gguf | GGUF | Q4_K_M | 1.67 GB | Download |
| lmcocktail-phi-2-v1.q5_k_m.gguf | GGUF | Q5_K_M | 1.93 GB | Download |
| lmcocktail-phi-2-v1.q6_k.gguf | GGUF | Q6_K | 2.13 GB | Download |
| lmcocktail-phi-2-v1.q8_0.gguf | GGUF | — | 2.75 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"-license": "other",
"-license_link": "https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE",
"-license_name": "microsoft-research-license",
"base_model": "Yhyu13/LMCocktail-phi-2-v1",
"inference": false,
"model_creator": "Yhyu13",
"model_name": "LMCocktail-phi-2-v1",
"pipeline_tag": "text-generation",
"quantized_by": "afrideva",
"tags": [
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0"
],
"frontmatter": {
"base_model": "Yhyu13/LMCocktail-phi-2-v1",
"inference": "false",
"model_creator": "Yhyu13",
"model_name": "LMCocktail-phi-2-v1",
"pipeline_tag": "text-generation",
"quantized_by": "afrideva",
"tags": [
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0"
]
},
"hero_image_url": "",
"summary": "This is a 50%-50% model of the phi2 alpca gpt4 and phi2 ultrachat200K models. https://huggingface.co/Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1 https://huggingface.co/venkycs/phi-2-ultrachat200k # Code The LM-cocktail is novel technique for merging multiple models https://arxiv.org/abs/2311.13534 Code is backed up by this repo https://github.com/FlagOpen/FlagEmbedding.git Merging scripts available under the ./scripts folder",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\n-license: other\n-license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE\n-license_name: microsoft-research-license\nbase_model: Yhyu13/LMCocktail-phi-2-v1\ninference: false\nmodel_creator: Yhyu13\nmodel_name: LMCocktail-phi-2-v1\npipeline_tag: text-generation\nquantized_by: afrideva\ntags:\n- gguf\n- ggml\n- quantized\n- q2_k\n- q3_k_m\n- q4_k_m\n- q5_k_m\n- q6_k\n- q8_0\n---\n# Yhyu13/LMCocktail-phi-2-v1-GGUF\n\nQuantized GGUF model files for [LMCocktail-phi-2-v1](https://huggingface.co/Yhyu13/LMCocktail-phi-2-v1) from [Yhyu13](https://huggingface.co/Yhyu13)\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [lmcocktail-phi-2-v1.fp16.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.fp16.gguf) | fp16 | 5.56 GB |\n| [lmcocktail-phi-2-v1.q2_k.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.q2_k.gguf) | q2_k | 1.17 GB |\n| [lmcocktail-phi-2-v1.q3_k_m.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.q3_k_m.gguf) | q3_k_m | 1.48 GB |\n| [lmcocktail-phi-2-v1.q4_k_m.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.q4_k_m.gguf) | q4_k_m | 1.79 GB |\n| [lmcocktail-phi-2-v1.q5_k_m.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.q5_k_m.gguf) | q5_k_m | 2.07 GB |\n| [lmcocktail-phi-2-v1.q6_k.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.q6_k.gguf) | q6_k | 2.29 GB |\n| [lmcocktail-phi-2-v1.q8_0.gguf](https://huggingface.co/afrideva/LMCocktail-phi-2-v1-GGUF/resolve/main/lmcocktail-phi-2-v1.q8_0.gguf) | q8_0 | 2.96 GB |\n\n\n\n## Original Model Card:\n# LM-cocktail phi-2 v1\n\n\nThis is a 50%-50% model of the phi2 alpca gpt4 and phi2 ultrachat200K models.\n\nhttps://huggingface.co/Yhyu13/phi-2-sft-alpaca_gpt4_en-ep1\n\nhttps://huggingface.co/venkycs/phi-2-ultrachat200k\n\n\n\n# Code\n\nThe LM-cocktail is novel technique for merging multiple models https://arxiv.org/abs/2311.13534\n\nCode is backed up by this repo https://github.com/FlagOpen/FlagEmbedding.git\n\nMerging scripts available under the [./scripts](./scripts) folder",
"related_quantizations": []
},
"tags": [
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0",
"text-generation",
"arxiv:2311.13534",
"base_model:Yhyu13/LMCocktail-phi-2-v1",
"base_model:quantized:Yhyu13/LMCocktail-phi-2-v1",
"region:us"
],
"likes": 0,
"downloads": 91,
"gated": false,
"private": false,
"last_modified": "2023-12-21T19:45:07.000Z",
"created_at": "2023-12-21T19:32:11.000Z",
"pipeline_tag": "text-generation",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "658492bbd7e1842dadbc2e64",
"id": "afrideva/LMCocktail-phi-2-v1-GGUF",
"modelId": "afrideva/LMCocktail-phi-2-v1-GGUF",
"sha": "9d9906b501866365ddb49d26dabfa3ba6ce3fda7",
"createdAt": "2023-12-21T19:32:11.000Z",
"lastModified": "2023-12-21T19:45:07.000Z",
"author": "afrideva",
"downloads": 91,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "",
"siblings_count": 9
}