richarderkhov/mnoukhov_-_pythia160m-sft-tldr-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of EleutherAI/pythia-160m-deduped on an unknown dataset. It achieves the following results on the evaluation set:",
    "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\npythia160m-sft-tldr - GGUF\n- Model creator: https://huggingface.co/mnoukhov/\n- Original model: https://huggingface.co/mnoukhov/pythia160m-sft-tldr/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [pythia160m-sft-tldr.Q2_K.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q2_K.gguf) | Q2_K | 0.07GB |\n| [pythia160m-sft-tldr.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.IQ3_XS.gguf) | IQ3_XS | 0.08GB |\n| [pythia160m-sft-tldr.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.IQ3_S.gguf) | IQ3_S | 0.08GB |\n| [pythia160m-sft-tldr.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q3_K_S.gguf) | Q3_K_S | 0.08GB |\n| [pythia160m-sft-tldr.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.IQ3_M.gguf) | IQ3_M | 0.08GB |\n| [pythia160m-sft-tldr.Q3_K.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q3_K.gguf) | Q3_K | 0.09GB |\n| [pythia160m-sft-tldr.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q3_K_M.gguf) | Q3_K_M | 0.09GB |\n| [pythia160m-sft-tldr.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q3_K_L.gguf) | Q3_K_L | 0.09GB |\n| [pythia160m-sft-tldr.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.IQ4_XS.gguf) | IQ4_XS | 0.09GB |\n| [pythia160m-sft-tldr.Q4_0.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q4_0.gguf) | Q4_0 | 0.1GB |\n| [pythia160m-sft-tldr.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.IQ4_NL.gguf) | IQ4_NL | 0.1GB |\n| [pythia160m-sft-tldr.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q4_K_S.gguf) | Q4_K_S | 0.1GB |\n| [pythia160m-sft-tldr.Q4_K.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q4_K.gguf) | Q4_K | 0.1GB |\n| [pythia160m-sft-tldr.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q4_K_M.gguf) | Q4_K_M | 0.1GB |\n| [pythia160m-sft-tldr.Q4_1.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q4_1.gguf) | Q4_1 | 0.1GB |\n| [pythia160m-sft-tldr.Q5_0.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q5_0.gguf) | Q5_0 | 0.11GB |\n| [pythia160m-sft-tldr.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q5_K_S.gguf) | Q5_K_S | 0.11GB |\n| [pythia160m-sft-tldr.Q5_K.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q5_K.gguf) | Q5_K | 0.12GB |\n| [pythia160m-sft-tldr.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q5_K_M.gguf) | Q5_K_M | 0.12GB |\n| [pythia160m-sft-tldr.Q5_1.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q5_1.gguf) | Q5_1 | 0.12GB |\n| [pythia160m-sft-tldr.Q6_K.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q6_K.gguf) | Q6_K | 0.13GB |\n| [pythia160m-sft-tldr.Q8_0.gguf](https://huggingface.co/RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf/blob/main/pythia160m-sft-tldr.Q8_0.gguf) | Q8_0 | 0.16GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nbase_model: EleutherAI/pythia-160m-deduped\ntags:\n- trl\n- sft\n- generated_from_trainer\nmodel-index:\n- name: pythia160m-sft-tldr\n  results: []\n---\n\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\nshould probably proofread and complete it, then remove this comment. -->\n\n# pythia160m-sft-tldr\n\nThis model is a fine-tuned version of [EleutherAI/pythia-160m-deduped](https://huggingface.co/EleutherAI/pythia-160m-deduped) on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 2.7993\n\n## Model description\n\nMore information needed\n\n## Intended uses & limitations\n\nMore information needed\n\n## Training and evaluation data\n\nMore information needed\n\n## Training procedure\n\n### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 16\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 1\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss |\n|:-------------:|:------:|:----:|:---------------:|\n| 3.2275        | 0.2007 | 183  | 2.8647          |\n| 2.8581        | 0.4013 | 366  | 2.8291          |\n| 2.8213        | 0.6020 | 549  | 2.8076          |\n| 2.799         | 0.8026 | 732  | 2.7993          |\n\n\n### Framework versions\n\n- Transformers 4.41.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 151,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-05T13:39:09.000Z",
  "created_at": "2024-07-05T13:37:15.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6687f70b7a49bb411cdc8a74",
  "id": "RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf",
  "modelId": "RichardErkhov/mnoukhov_-_pythia160m-sft-tldr-gguf",
  "sha": "72ed2c05afb675ff7905e196fb18ce1f0e851ccd",
  "createdAt": "2024-07-05T13:37:15.000Z",
  "lastModified": "2024-07-05T13:39:09.000Z",
  "author": "RichardErkhov",
  "downloads": 151,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}