Model Intelligence Sheet
richarderkhov/miguel-kjh_-_pythia-14m-gguf overview
This model is a fine-tuned version of EleutherAI/pythia-14m. It has been trained using TRL.
Downloads
98
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 |
|---|---|---|---|---|
| pythia-14m.IQ3_M.gguf | GGUF | IQ3_M | 12.34 MB | Download |
| pythia-14m.IQ3_S.gguf | GGUF | IQ3_S | 12.29 MB | Download |
| pythia-14m.IQ3_XS.gguf | GGUF | IQ3_XS | 12.29 MB | Download |
| pythia-14m.IQ4_NL.gguf | GGUF | IQ4_NL | 12.34 MB | Download |
| pythia-14m.IQ4_XS.gguf | GGUF | IQ4_XS | 12.33 MB | Download |
| pythia-14m.Q2_K.gguf | GGUF | Q2_K | 12.29 MB | Download |
| pythia-14m.Q3_K.gguf | GGUF | Q3_K | 12.39 MB | Download |
| pythia-14m.Q3_K_L.gguf | GGUF | Q3_K_L | 12.44 MB | Download |
| pythia-14m.Q3_K_M.gguf | GGUF | Q3_K_M | 12.39 MB | Download |
| pythia-14m.Q3_K_S.gguf | GGUF | Q3_K_S | 12.29 MB | Download |
| pythia-14m.Q4_0.gguf | GGUF | — | 12.34 MB | Download |
| pythia-14m.Q4_1.gguf | GGUF | — | 12.80 MB | Download |
| pythia-14m.Q4_K.gguf | GGUF | Q4_K | 13.25 MB | Download |
| pythia-14m.Q4_K_M.gguf | GGUF | Q4_K_M | 13.25 MB | Download |
| pythia-14m.Q4_K_S.gguf | GGUF | Q4_K_S | 13.20 MB | Download |
| pythia-14m.Q5_0.gguf | GGUF | — | 13.25 MB | Download |
| pythia-14m.Q5_1.gguf | GGUF | — | 13.70 MB | Download |
| pythia-14m.Q5_K.gguf | GGUF | Q5_K | 13.79 MB | Download |
| pythia-14m.Q5_K_M.gguf | GGUF | Q5_K_M | 13.79 MB | Download |
| pythia-14m.Q5_K_S.gguf | GGUF | Q5_K_S | 13.68 MB | Download |
| pythia-14m.Q6_K.gguf | GGUF | Q6_K | 15.88 MB | Download |
| pythia-14m.Q8_0.gguf | GGUF | — | 15.97 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg",
"summary": "This model is a fine-tuned version of EleutherAI/pythia-14m. It has been trained using TRL.",
"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\npythia-14m - GGUF\n- Model creator: https://huggingface.co/miguel-kjh/\n- Original model: https://huggingface.co/miguel-kjh/pythia-14m/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [pythia-14m.Q2_K.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q2_K.gguf) | Q2_K | 0.01GB |\n| [pythia-14m.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.IQ3_XS.gguf) | IQ3_XS | 0.01GB |\n| [pythia-14m.IQ3_S.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.IQ3_S.gguf) | IQ3_S | 0.01GB |\n| [pythia-14m.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q3_K_S.gguf) | Q3_K_S | 0.01GB |\n| [pythia-14m.IQ3_M.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.IQ3_M.gguf) | IQ3_M | 0.01GB |\n| [pythia-14m.Q3_K.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q3_K.gguf) | Q3_K | 0.01GB |\n| [pythia-14m.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q3_K_M.gguf) | Q3_K_M | 0.01GB |\n| [pythia-14m.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q3_K_L.gguf) | Q3_K_L | 0.01GB |\n| [pythia-14m.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.IQ4_XS.gguf) | IQ4_XS | 0.01GB |\n| [pythia-14m.Q4_0.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q4_0.gguf) | Q4_0 | 0.01GB |\n| [pythia-14m.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.IQ4_NL.gguf) | IQ4_NL | 0.01GB |\n| [pythia-14m.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q4_K_S.gguf) | Q4_K_S | 0.01GB |\n| [pythia-14m.Q4_K.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q4_K.gguf) | Q4_K | 0.01GB |\n| [pythia-14m.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q4_K_M.gguf) | Q4_K_M | 0.01GB |\n| [pythia-14m.Q4_1.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q4_1.gguf) | Q4_1 | 0.01GB |\n| [pythia-14m.Q5_0.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q5_0.gguf) | Q5_0 | 0.01GB |\n| [pythia-14m.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q5_K_S.gguf) | Q5_K_S | 0.01GB |\n| [pythia-14m.Q5_K.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q5_K.gguf) | Q5_K | 0.01GB |\n| [pythia-14m.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q5_K_M.gguf) | Q5_K_M | 0.01GB |\n| [pythia-14m.Q5_1.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q5_1.gguf) | Q5_1 | 0.01GB |\n| [pythia-14m.Q6_K.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q6_K.gguf) | Q6_K | 0.02GB |\n| [pythia-14m.Q8_0.gguf](https://huggingface.co/RichardErkhov/miguel-kjh_-_pythia-14m-gguf/blob/main/pythia-14m.Q8_0.gguf) | Q8_0 | 0.02GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: EleutherAI/pythia-14m\nlibrary_name: transformers\nmodel_name: pythia-14m\ntags:\n- generated_from_trainer\n- trl\n- sft\nlicence: license\n---\n\n# Model Card for pythia-14m\n\nThis model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m).\nIt has been trained using [TRL](https://github.com/huggingface/trl).\n\n## Quick start\n\n```python\nfrom transformers import pipeline\n\nquestion = \"If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?\"\ngenerator = pipeline(\"text-generation\", model=\"miguel-kjh/pythia-14m\", device=\"cuda\")\noutput = generator([{\"role\": \"user\", \"content\": question}], max_new_tokens=128, return_full_text=False)[0]\nprint(output[\"generated_text\"])\n```\n\n## Training procedure\n\n[<img src=\"https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg\" alt=\"Visualize in Weights & Biases\" width=\"150\" height=\"24\"/>](https://wandb.ai/miguel_kjh/huggingface/runs/zy7xcvsv)\n\nThis model was trained with SFT.\n\n### Framework versions\n\n- TRL: 0.12.1\n- Transformers: 4.46.3\n- Pytorch: 2.3.1+cu118\n- Datasets: 3.1.0\n- Tokenizers: 0.20.3\n\n## Citations\n\n\n\nCite TRL as:\n \n```bibtex\n@misc{vonwerra2022trl,\n\ttitle = {{TRL: Transformer Reinforcement Learning}},\n\tauthor = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},\n\tyear = 2020,\n\tjournal = {GitHub repository},\n\tpublisher = {GitHub},\n\thowpublished = {\\url{https://github.com/huggingface/trl}}\n}\n```\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 98,
"gated": false,
"private": false,
"last_modified": "2025-02-09T21:58:41.000Z",
"created_at": "2025-02-09T21:57:14.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "67a924ba7f85620bad6e3d56",
"id": "RichardErkhov/miguel-kjh_-_pythia-14m-gguf",
"modelId": "RichardErkhov/miguel-kjh_-_pythia-14m-gguf",
"sha": "f7a38b6a8cc874b1049129df5f7d60addadcfdb4",
"createdAt": "2025-02-09T21:57:14.000Z",
"lastModified": "2025-02-09T21:58:41.000Z",
"author": "RichardErkhov",
"downloads": 98,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}