Model Intelligence Sheet
richarderkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf overview
Model Description Mistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation. The dataset has been pre-processed by doing the following: 1. remove all refusals 2. remove any mention of AI assistant 3. split any multi-turn dialog generated in the dataset into multi-turn conversations records
Downloads
184
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
22 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| mistral-7b-v0.1-layla-v3.IQ3_M.gguf | GGUF | IQ3_M | 3.06 GB | Download |
| mistral-7b-v0.1-layla-v3.IQ3_S.gguf | GGUF | IQ3_S | 2.96 GB | Download |
| mistral-7b-v0.1-layla-v3.IQ3_XS.gguf | GGUF | IQ3_XS | 2.81 GB | Download |
| mistral-7b-v0.1-layla-v3.IQ4_NL.gguf | GGUF | IQ4_NL | 3.87 GB | Download |
| mistral-7b-v0.1-layla-v3.IQ4_XS.gguf | GGUF | IQ4_XS | 3.67 GB | Download |
| mistral-7b-v0.1-layla-v3.Q2_K.gguf | GGUF | Q2_K | 2.53 GB | Download |
| mistral-7b-v0.1-layla-v3.Q3_K.gguf | GGUF | Q3_K | 3.28 GB | Download |
| mistral-7b-v0.1-layla-v3.Q3_K_L.gguf | GGUF | Q3_K_L | 3.56 GB | Download |
| mistral-7b-v0.1-layla-v3.Q3_K_M.gguf | GGUF | Q3_K_M | 3.28 GB | Download |
| mistral-7b-v0.1-layla-v3.Q3_K_S.gguf | GGUF | Q3_K_S | 2.95 GB | Download |
| mistral-7b-v0.1-layla-v3.Q4_0.gguf | GGUF | — | 3.83 GB | Download |
| mistral-7b-v0.1-layla-v3.Q4_1.gguf | GGUF | — | 4.24 GB | Download |
| mistral-7b-v0.1-layla-v3.Q4_K.gguf | GGUF | Q4_K | 4.07 GB | Download |
| mistral-7b-v0.1-layla-v3.Q4_K_M.gguf | GGUF | Q4_K_M | 4.07 GB | Download |
| mistral-7b-v0.1-layla-v3.Q4_K_S.gguf | GGUF | Q4_K_S | 3.86 GB | Download |
| mistral-7b-v0.1-layla-v3.Q5_0.gguf | GGUF | — | 4.65 GB | Download |
| mistral-7b-v0.1-layla-v3.Q5_1.gguf | GGUF | — | 5.07 GB | Download |
| mistral-7b-v0.1-layla-v3.Q5_K.gguf | GGUF | Q5_K | 4.78 GB | Download |
| mistral-7b-v0.1-layla-v3.Q5_K_M.gguf | GGUF | Q5_K_M | 4.78 GB | Download |
| mistral-7b-v0.1-layla-v3.Q5_K_S.gguf | GGUF | Q5_K_S | 4.65 GB | Download |
| mistral-7b-v0.1-layla-v3.Q6_K.gguf | GGUF | Q6_K | 5.53 GB | Download |
| mistral-7b-v0.1-layla-v3.Q8_0.gguf | GGUF | — | 7.17 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png",
"summary": "### Model Description Mistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation. The dataset has been pre-processed by doing the following: 1. remove all refusals 2. remove any mention of AI assistant 3. split any multi-turn dialog generated in the dataset into multi-turn conversations records",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nmistral-7b-v0.1-layla-v3 - GGUF\n- Model creator: https://huggingface.co/l3utterfly/\n- Original model: https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v3/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [mistral-7b-v0.1-layla-v3.Q2_K.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q2_K.gguf) | Q2_K | 2.53GB |\n| [mistral-7b-v0.1-layla-v3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [mistral-7b-v0.1-layla-v3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [mistral-7b-v0.1-layla-v3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [mistral-7b-v0.1-layla-v3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [mistral-7b-v0.1-layla-v3.Q3_K.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q3_K.gguf) | Q3_K | 3.28GB |\n| [mistral-7b-v0.1-layla-v3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [mistral-7b-v0.1-layla-v3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [mistral-7b-v0.1-layla-v3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [mistral-7b-v0.1-layla-v3.Q4_0.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [mistral-7b-v0.1-layla-v3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [mistral-7b-v0.1-layla-v3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [mistral-7b-v0.1-layla-v3.Q4_K.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q4_K.gguf) | Q4_K | 4.07GB |\n| [mistral-7b-v0.1-layla-v3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [mistral-7b-v0.1-layla-v3.Q4_1.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [mistral-7b-v0.1-layla-v3.Q5_0.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [mistral-7b-v0.1-layla-v3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [mistral-7b-v0.1-layla-v3.Q5_K.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q5_K.gguf) | Q5_K | 4.78GB |\n| [mistral-7b-v0.1-layla-v3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [mistral-7b-v0.1-layla-v3.Q5_1.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [mistral-7b-v0.1-layla-v3.Q6_K.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q6_K.gguf) | Q6_K | 5.53GB |\n| [mistral-7b-v0.1-layla-v3.Q8_0.gguf](https://huggingface.co/RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf/blob/main/mistral-7b-v0.1-layla-v3.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nlanguage:\n- en\n---\n\n# Model Card\n\n### Model Description\n\nMistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.\n\nThe dataset has been pre-processed by doing the following:\n1. remove all refusals\n2. remove any mention of AI assistant\n3. split any multi-turn dialog generated in the dataset into multi-turn conversations records\n\n- **Developed by:** l3utterfly\n- **Funded by:** Layla Network\n- **Model type:** Mistral\n- **Language(s) (NLP):** English\n- **License:** Apache-2.0\n- **Finetuned from model:** Mistral 7B\n\n## Uses\n\nBase model used by Layla - the offline personal assistant: https://www.layla-network.ai\n\nHelp & support: https://discord.gg/x546YJ6nYC\n\nPrompt:\n```\nUSER:\nASSISTANT:\n```\n\n[<img src=\"https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png\" alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>](https://github.com/OpenAccess-AI-Collective/axolotl)\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 184,
"gated": false,
"private": false,
"last_modified": "2024-09-22T07:12:25.000Z",
"created_at": "2024-09-22T04:55:25.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "66efa33d1928e7fe9ca5fe31",
"id": "RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf",
"modelId": "RichardErkhov/l3utterfly_-_mistral-7b-v0.1-layla-v3-gguf",
"sha": "e7a4c2555813ccc30fc40c7b9ae617e6d3616bc9",
"createdAt": "2024-09-22T04:55:25.000Z",
"lastModified": "2024-09-22T07:12:25.000Z",
"author": "RichardErkhov",
"downloads": 184,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}