Model Intelligence Sheet
xaviviro/elchato-0.1-1.1b-gguf overview
!ElChato ElChato és el modelo más pequeño de chat en lengua castellana. És el resultado de finetunear el modelo TinyLlama-1.1B-Chat-v1.0 con las instrucciones de OpenAssistant v2 traducidas automáticamente al castellano con recursos de Helsinki-NLP y tratadas en formato ChatGLM3.
Downloads
90
Likes
2
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
15 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| ElChato-0.1-1.1b_f16.gguf | GGUF | F16 | 2.05 GB | Download |
| ElChato-0.1-1.1b_q2_k.gguf | GGUF | Q2_K | 459.81 MB | Download |
| ElChato-0.1-1.1b_q3_k_l.gguf | GGUF | Q3_K_L | 564.12 MB | Download |
| ElChato-0.1-1.1b_q3_k_m.gguf | GGUF | Q3_K_M | 524.37 MB | Download |
| ElChato-0.1-1.1b_q3_k_s.gguf | GGUF | Q3_K_S | 476.21 MB | Download |
| ElChato-0.1-1.1b_q4_0.gguf | GGUF | — | 607.23 MB | Download |
| ElChato-0.1-1.1b_q4_1.gguf | GGUF | — | 668.89 MB | Download |
| ElChato-0.1-1.1b_q4_k_m.gguf | GGUF | Q4_K_M | 636.88 MB | Download |
| ElChato-0.1-1.1b_q4_k_s.gguf | GGUF | Q4_K_S | 612.98 MB | Download |
| ElChato-0.1-1.1b_q5_0.gguf | GGUF | — | 730.54 MB | Download |
| ElChato-0.1-1.1b_q5_1.gguf | GGUF | — | 792.20 MB | Download |
| ElChato-0.1-1.1b_q5_k_m.gguf | GGUF | Q5_K_M | 745.82 MB | Download |
| ElChato-0.1-1.1b_q5_k_s.gguf | GGUF | Q5_K_S | 730.54 MB | Download |
| ElChato-0.1-1.1b_q6_k.gguf | GGUF | Q6_K | 861.56 MB | Download |
| ElChato-0.1-1.1b_q8_0.gguf | GGUF | — | 1.09 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "apache-2.0",
"language": [
"es"
],
"model_creator": "xaviviro",
"model_name": "PetitXat-0.1-1.1b",
"prompt_template": "<|system|>\\n{system}</s>\\n<|user|>{instruction}</s>\\n<|assistant|>\\n",
"frontmatter": {
"license": "apache-2.0",
"language": [
"es"
],
"model_creator": "xaviviro",
"model_name": "PetitXat-0.1-1.1b",
"prompt_template": "<|system|>\\n{system}</s>\\n<|user|>{instruction}</s>\\n<|assistant|>\\n"
},
"hero_image_url": "elchato.png",
"summary": "!ElChato ElChato és el modelo más pequeño de chat en lengua castellana. És el resultado de finetunear el modelo TinyLlama-1.1B-Chat-v1.0 con las instrucciones de OpenAssistant v2 traducidas automáticamente al castellano con recursos de Helsinki-NLP y tratadas en formato ChatGLM3.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- es\nmodel_creator: xaviviro\nmodel_name: PetitXat-0.1-1.1b\nprompt_template: <|system|>\\n{system}</s>\\n<|user|>{instruction}</s>\\n<|assistant|>\\n\n---\n\n\n# ElChato 1.1B: El modelo más pequeño de chat en lengua castellana\n\n\n\nElChato és el modelo más pequeño de chat en lengua castellana. És el resultado de finetunear el modelo [TinyLlama-1.1B-Chat-v1.0](/TinyLlama/TinyLlama-1.1B-Chat-v1.0) con las instrucciones de [OpenAssistant v2](/datasets/OpenAssistant/oasst2) traducidas automáticamente al castellano con recursos de [Helsinki-NLP](/Helsinki-NLP) y tratadas en formato ChatGLM3.\n\n## Formato del prompt\n\n```\n<|system|>\nEres un buen asistente</s>\n<|user|>\n¿Quién fue Isaac Newton?</s>\n<|assistant|>\n```",
"related_quantizations": []
},
"tags": [
"gguf",
"es",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 2,
"downloads": 90,
"gated": false,
"private": false,
"last_modified": "2024-01-12T21:38:18.000Z",
"created_at": "2024-01-04T07:08:20.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "659659648174ea23bce8f704",
"id": "xaviviro/ElChato-0.1-1.1b-GGUF",
"modelId": "xaviviro/ElChato-0.1-1.1b-GGUF",
"sha": "1b33aaab15703d12b15bf61a26a9852323a9f201",
"createdAt": "2024-01-04T07:08:20.000Z",
"lastModified": "2024-01-12T21:38:18.000Z",
"author": "xaviviro",
"downloads": 90,
"likes": 2,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 18
}