Model Intelligence Sheet
richarderkhov/hy-kdpark_-_llama-2-koen-13b-sft-v0.3-gguf overview
Quantization made by Richard Erkhov. Github Discord Request more models llama-2-koen-13b-sft-v0.3 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | llama-2-koen-13b-sft-v0.3.Q2K.gguf | Q2K | 4.6GB | | llama-2-koen-13b-sft-v0.3.IQ3XS.gguf | IQ3XS | 5.08GB | | llama-2-koen-13b-sft-v0.3.IQ3S.gguf | IQ3S | 5.36GB | | llama-2-koen-13b-sft-v0.3.Q3KS.gguf | Q3KS | 5.36GB | | llama-2-koen-13b-sft-v0.3.IQ3M.gguf | IQ3M | 5.66GB | | llama-2-koen-13b-sft-v0.3.Q3K.gguf | Q3K | 5.99GB | | llama-2-koen-13b-sft-v0.3.Q3KM.gguf | Q3KM | 5.99GB | | llama-2-koen-13b-sft-v0.3.Q3KL.gguf | Q3KL | 6.54GB | | llama-2-koen-13b-sft-v0.3.IQ4XS.gguf | IQ4XS | 6.63GB | | llama-2-koen-13b-sft-v0.3.Q40.gguf | Q40 | 6.95GB | | llama-2-koen-13b-sft-v0.3.IQ4NL.gguf | IQ4NL | 7.0GB | | llama-2-koen-13b-sft-v0.3.Q4KS.gguf | Q4KS | 7.01GB | | llama-2-koen-13b-sft-v0.3.Q4K.gguf | Q4K | 7.42GB | | llama-2-koen-13b-sft-v0.3.Q4KM.gguf | Q4KM | 7.42GB | | llama-2-koen-13b-sft-v0.3.Q41.gguf | Q41 | 7.71GB | | llama-2-koen-13b-sft-v0.3.Q50.gguf | Q50 | 8.46GB | | llama-2-koen-13b-sft-v0.3.Q5KS.gguf | Q5KS | 8.46GB | | llama-2-koen-13b-sft-v0.3.Q5K.gguf | Q5K | 8.7GB | | llama-2-koen-13b-sft-v0.3.Q5KM.gguf | Q5KM | 8.7GB | | llama-2-koen-13b-sft-v0.3.Q51.gguf | Q51 | 9.21GB | | llama-2-koen-13b-sft-v0.3.Q6K.gguf | Q6K | 10.06GB | | llama-2-koen-13b-sft-v0.3.Q80.gguf | Q80 | 13.03GB | Original model description: --- license: cc-by-nc-sa-4.0 ---
Downloads
109
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 |
|---|---|---|---|---|
| llama-2-koen-13b-sft-v0.3.IQ3_M.gguf | GGUF | IQ3_M | 5.66 GB | Download |
| llama-2-koen-13b-sft-v0.3.IQ3_S.gguf | GGUF | IQ3_S | 5.36 GB | Download |
| llama-2-koen-13b-sft-v0.3.IQ3_XS.gguf | GGUF | IQ3_XS | 5.08 GB | Download |
| llama-2-koen-13b-sft-v0.3.IQ4_NL.gguf | GGUF | IQ4_NL | 7.00 GB | Download |
| llama-2-koen-13b-sft-v0.3.IQ4_XS.gguf | GGUF | IQ4_XS | 6.63 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q2_K.gguf | GGUF | Q2_K | 4.60 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q3_K.gguf | GGUF | Q3_K | 5.99 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q3_K_L.gguf | GGUF | Q3_K_L | 6.54 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q3_K_M.gguf | GGUF | Q3_K_M | 5.99 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q3_K_S.gguf | GGUF | Q3_K_S | 5.36 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q4_0.gguf | GGUF | — | 6.95 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q4_1.gguf | GGUF | — | 7.71 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q4_K.gguf | GGUF | Q4_K | 7.42 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q4_K_M.gguf | GGUF | Q4_K_M | 7.42 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q4_K_S.gguf | GGUF | Q4_K_S | 7.01 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q5_0.gguf | GGUF | — | 8.46 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q5_1.gguf | GGUF | — | 9.21 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q5_K.gguf | GGUF | Q5_K | 8.70 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q5_K_M.gguf | GGUF | Q5_K_M | 8.70 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q5_K_S.gguf | GGUF | Q5_K_S | 8.46 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q6_K.gguf | GGUF | Q6_K | 10.06 GB | Download |
| llama-2-koen-13b-sft-v0.3.Q8_0.gguf | GGUF | — | 13.03 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "Quantization made by Richard Erkhov. Github Discord Request more models llama-2-koen-13b-sft-v0.3 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | llama-2-koen-13b-sft-v0.3.Q2_K.gguf | Q2_K | 4.6GB | | llama-2-koen-13b-sft-v0.3.IQ3_XS.gguf | IQ3_XS | 5.08GB | | llama-2-koen-13b-sft-v0.3.IQ3_S.gguf | IQ3_S | 5.36GB | | llama-2-koen-13b-sft-v0.3.Q3_K_S.gguf | Q3_K_S | 5.36GB | | llama-2-koen-13b-sft-v0.3.IQ3_M.gguf | IQ3_M | 5.66GB | | llama-2-koen-13b-sft-v0.3.Q3_K.gguf | Q3_K | 5.99GB | | llama-2-koen-13b-sft-v0.3.Q3_K_M.gguf | Q3_K_M | 5.99GB | | llama-2-koen-13b-sft-v0.3.Q3_K_L.gguf | Q3_K_L | 6.54GB | | llama-2-koen-13b-sft-v0.3.IQ4_XS.gguf | IQ4_XS | 6.63GB | | llama-2-koen-13b-sft-v0.3.Q4_0.gguf | Q4_0 | 6.95GB | | llama-2-koen-13b-sft-v0.3.IQ4_NL.gguf | IQ4_NL | 7.0GB | | llama-2-koen-13b-sft-v0.3.Q4_K_S.gguf | Q4_K_S | 7.01GB | | llama-2-koen-13b-sft-v0.3.Q4_K.gguf | Q4_K | 7.42GB | | llama-2-koen-13b-sft-v0.3.Q4_K_M.gguf | Q4_K_M | 7.42GB | | llama-2-koen-13b-sft-v0.3.Q4_1.gguf | Q4_1 | 7.71GB | | llama-2-koen-13b-sft-v0.3.Q5_0.gguf | Q5_0 | 8.46GB | | llama-2-koen-13b-sft-v0.3.Q5_K_S.gguf | Q5_K_S | 8.46GB | | llama-2-koen-13b-sft-v0.3.Q5_K.gguf | Q5_K | 8.7GB | | llama-2-koen-13b-sft-v0.3.Q5_K_M.gguf | Q5_K_M | 8.7GB | | llama-2-koen-13b-sft-v0.3.Q5_1.gguf | Q5_1 | 9.21GB | | llama-2-koen-13b-sft-v0.3.Q6_K.gguf | Q6_K | 10.06GB | | llama-2-koen-13b-sft-v0.3.Q8_0.gguf | Q8_0 | 13.03GB | Original model description: --- license: cc-by-nc-sa-4.0 ---",
"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\nllama-2-koen-13b-sft-v0.3 - GGUF\n- Model creator: https://huggingface.co/HY-KDPARK/\n- Original model: https://huggingface.co/HY-KDPARK/llama-2-koen-13b-sft-v0.3/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama-2-koen-13b-sft-v0.3.Q2_K.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q2_K.gguf) | Q2_K | 4.6GB |\n| [llama-2-koen-13b-sft-v0.3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.IQ3_XS.gguf) | IQ3_XS | 5.08GB |\n| [llama-2-koen-13b-sft-v0.3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.IQ3_S.gguf) | IQ3_S | 5.36GB |\n| [llama-2-koen-13b-sft-v0.3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q3_K_S.gguf) | Q3_K_S | 5.36GB |\n| [llama-2-koen-13b-sft-v0.3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.IQ3_M.gguf) | IQ3_M | 5.66GB |\n| [llama-2-koen-13b-sft-v0.3.Q3_K.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q3_K.gguf) | Q3_K | 5.99GB |\n| [llama-2-koen-13b-sft-v0.3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q3_K_M.gguf) | Q3_K_M | 5.99GB |\n| [llama-2-koen-13b-sft-v0.3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q3_K_L.gguf) | Q3_K_L | 6.54GB |\n| [llama-2-koen-13b-sft-v0.3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.IQ4_XS.gguf) | IQ4_XS | 6.63GB |\n| [llama-2-koen-13b-sft-v0.3.Q4_0.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q4_0.gguf) | Q4_0 | 6.95GB |\n| [llama-2-koen-13b-sft-v0.3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.IQ4_NL.gguf) | IQ4_NL | 7.0GB |\n| [llama-2-koen-13b-sft-v0.3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q4_K_S.gguf) | Q4_K_S | 7.01GB |\n| [llama-2-koen-13b-sft-v0.3.Q4_K.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q4_K.gguf) | Q4_K | 7.42GB |\n| [llama-2-koen-13b-sft-v0.3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q4_K_M.gguf) | Q4_K_M | 7.42GB |\n| [llama-2-koen-13b-sft-v0.3.Q4_1.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q4_1.gguf) | Q4_1 | 7.71GB |\n| [llama-2-koen-13b-sft-v0.3.Q5_0.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q5_0.gguf) | Q5_0 | 8.46GB |\n| [llama-2-koen-13b-sft-v0.3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q5_K_S.gguf) | Q5_K_S | 8.46GB |\n| [llama-2-koen-13b-sft-v0.3.Q5_K.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q5_K.gguf) | Q5_K | 8.7GB |\n| [llama-2-koen-13b-sft-v0.3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q5_K_M.gguf) | Q5_K_M | 8.7GB |\n| [llama-2-koen-13b-sft-v0.3.Q5_1.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q5_1.gguf) | Q5_1 | 9.21GB |\n| [llama-2-koen-13b-sft-v0.3.Q6_K.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q6_K.gguf) | Q6_K | 10.06GB |\n| [llama-2-koen-13b-sft-v0.3.Q8_0.gguf](https://huggingface.co/RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf/blob/main/llama-2-koen-13b-sft-v0.3.Q8_0.gguf) | Q8_0 | 13.03GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-sa-4.0\n---\n\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 109,
"gated": false,
"private": false,
"last_modified": "2024-08-03T02:36:28.000Z",
"created_at": "2024-08-02T20:27:12.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "66ad41205e5eb85a00c5e2eb",
"id": "RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf",
"modelId": "RichardErkhov/HY-KDPARK_-_llama-2-koen-13b-sft-v0.3-gguf",
"sha": "549b2c4021d6fdb072da341da67df65c6002008b",
"createdAt": "2024-08-02T20:27:12.000Z",
"lastModified": "2024-08-03T02:36:28.000Z",
"author": "RichardErkhov",
"downloads": 109,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}