richarderkhov/ryanyr_-_reflect_llama8b_om2-300k_sft-t1_lr1e-6-gguf overview

{
  "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 meta-llama/Llama-3.1-8B-Instruct. 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\nreflect_llama8B_om2-300k_sft-t1_lr1e-6 - GGUF\n- Model creator: https://huggingface.co/RyanYr/\n- Original model: https://huggingface.co/RyanYr/reflect_llama8B_om2-300k_sft-t1_lr1e-6/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q2_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q2_K.gguf) | Q2_K | 2.96GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ3_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ3_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K.gguf) | Q3_K | 3.74GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_K.gguf) | Q4_K | 4.58GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_1.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_K.gguf) | Q5_K | 5.34GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_1.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q6_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q6_K.gguf) | Q6_K | 6.14GB |\n| [reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q8_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf/blob/main/reflect_llama8B_om2-300k_sft-t1_lr1e-6.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: meta-llama/Llama-3.1-8B-Instruct\nlibrary_name: transformers\nmodel_name: reflect_llama8B_om2-300k_sft-t1_lr1e-6\ntags:\n- generated_from_trainer\n- trl\n- sft\nlicence: license\n---\n\n# Model Card for reflect_llama8B_om2-300k_sft-t1_lr1e-6\n\nThis model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).\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=\"RyanYr/reflect_llama8B_om2-300k_sft-t1_lr1e-6\", 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/yyr/huggingface/runs/zpxht3ku)\n\nThis model was trained with SFT.\n\n### Framework versions\n\n- TRL: 0.12.0.dev0\n- Transformers: 4.45.2\n- Pytorch: 2.5.1\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",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1590,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-07T16:50:52.000Z",
  "created_at": "2025-07-07T15:48:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "686bec672b68faf110c0c39b",
  "id": "RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf",
  "modelId": "RichardErkhov/RyanYr_-_reflect_llama8B_om2-300k_sft-t1_lr1e-6-gguf",
  "sha": "15d052de0ea5f3a4714ba776a5ca06741b7485ef",
  "createdAt": "2025-07-07T15:48:55.000Z",
  "lastModified": "2025-07-07T16:50:52.000Z",
  "author": "RichardErkhov",
  "downloads": 1590,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}