goekdeniz-guelmez/hyperion-2.1-mistral-7b-gguf 7b.Q8_0 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
goekdeniz-guelmez/hyperion-2.1-mistral-7b-gguf overview
This model is very compliant. It will respond to any request without refusal. If you intend to deploy this model at an enterprise level, I would recommend aligning this model using DPO.
Downloads
150
Likes
1
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
14 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| hyperion-2.1-mistral-7b.Q2_K.gguf | GGUF | Q2_K | 2.53 GB | Download |
| hyperion-2.1-mistral-7b.Q3_K_L.gguf | GGUF | Q3_K_L | 3.56 GB | Download |
| hyperion-2.1-mistral-7b.Q3_K_M.gguf | GGUF | Q3_K_M | 3.28 GB | Download |
| hyperion-2.1-mistral-7b.Q3_K_S.gguf | GGUF | Q3_K_S | 2.95 GB | Download |
| hyperion-2.1-mistral-7b.Q4_0.gguf | GGUF | — | 3.83 GB | Download |
| hyperion-2.1-mistral-7b.Q4_1.gguf | GGUF | — | 4.24 GB | Download |
| hyperion-2.1-mistral-7b.Q4_K_M.gguf | GGUF | Q4_K_M | 4.07 GB | Download |
| hyperion-2.1-mistral-7b.Q4_K_S.gguf | GGUF | Q4_K_S | 3.86 GB | Download |
| hyperion-2.1-mistral-7b.Q5_0.gguf | GGUF | — | 4.65 GB | Download |
| hyperion-2.1-mistral-7b.Q5_1.gguf | GGUF | — | 5.07 GB | Download |
| hyperion-2.1-mistral-7b.Q5_K_M.gguf | GGUF | Q5_K_M | 4.78 GB | Download |
| hyperion-2.1-mistral-7b.Q5_K_S.gguf | GGUF | Q5_K_S | 4.65 GB | Download |
| hyperion-2.1-mistral-7b.Q6_K.gguf | GGUF | Q6_K | 5.53 GB | Download |
| hyperion-2.1-mistral-7b.Q8_0.gguf | GGUF | — | 7.17 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"library_name": "transformers",
"license": "apache-2.0",
"datasets": [
"Locutusque/hyperion-v2.0"
],
"language": [
"en"
],
"frontmatter": {
"library_name": "transformers",
"license": "apache-2.0",
"datasets": [
"Locutusque/hyperion-v2.0"
],
"language": [
"en"
]
},
"hero_image_url": "",
"summary": "This model is very compliant. It will respond to any request without refusal. If you intend to deploy this model at an enterprise level, I would recommend aligning this model using DPO.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlibrary_name: transformers\nlicense: apache-2.0\ndatasets:\n- Locutusque/hyperion-v2.0\nlanguage:\n- en\n---\n# Description\nFurther fine-tuned Locutusque/Hyperion-2.0-Mistral-7B at a higher learning rate. This was done to see if performance increased. Read Locutusque/Hyperion-2.0-Mistral-7B's model card for more information. Slight performance gain was observed. More checkpoints will be released in the future.\n\n# Disclaimer\n\nThis model is very compliant. It will respond to any request without refusal. If you intend to deploy this model at an enterprise level, I would recommend aligning this model using DPO.",
"related_quantizations": []
},
"tags": [
"transformers",
"safetensors",
"gguf",
"mistral",
"text-generation",
"en",
"dataset:Locutusque/hyperion-v2.0",
"license:apache-2.0",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"likes": 1,
"downloads": 150,
"gated": false,
"private": false,
"last_modified": "2024-03-10T19:57:38.000Z",
"created_at": "2024-03-10T19:32:23.000Z",
"pipeline_tag": "text-generation",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "65ee0ac74064c103dd19f98d",
"id": "Goekdeniz-Guelmez/Hyperion-2.1-Mistral-7B-GGUF",
"modelId": "Goekdeniz-Guelmez/Hyperion-2.1-Mistral-7B-GGUF",
"sha": "0cdd438ba9deb8696cf7814cada12e2105e0e21b",
"createdAt": "2024-03-10T19:32:23.000Z",
"lastModified": "2024-03-10T19:57:38.000Z",
"author": "Goekdeniz-Guelmez",
"downloads": 150,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "transformers",
"siblings_count": 32
}