richarderkhov/konqueror3891_-_hw2-orpo-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of openai-community/gpt2 on the piqa 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\nHW2-orpo - GGUF\n- Model creator: https://huggingface.co/KoNqUeRoR3891/\n- Original model: https://huggingface.co/KoNqUeRoR3891/HW2-orpo/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [HW2-orpo.Q2_K.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q2_K.gguf) | Q2_K | 0.08GB |\n| [HW2-orpo.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.IQ3_XS.gguf) | IQ3_XS | 0.08GB |\n| [HW2-orpo.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.IQ3_S.gguf) | IQ3_S | 0.08GB |\n| [HW2-orpo.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q3_K_S.gguf) | Q3_K_S | 0.08GB |\n| [HW2-orpo.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.IQ3_M.gguf) | IQ3_M | 0.09GB |\n| [HW2-orpo.Q3_K.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q3_K.gguf) | Q3_K | 0.09GB |\n| [HW2-orpo.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q3_K_M.gguf) | Q3_K_M | 0.09GB |\n| [HW2-orpo.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q3_K_L.gguf) | Q3_K_L | 0.1GB |\n| [HW2-orpo.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.IQ4_XS.gguf) | IQ4_XS | 0.1GB |\n| [HW2-orpo.Q4_0.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q4_0.gguf) | Q4_0 | 0.1GB |\n| [HW2-orpo.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.IQ4_NL.gguf) | IQ4_NL | 0.1GB |\n| [HW2-orpo.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q4_K_S.gguf) | Q4_K_S | 0.1GB |\n| [HW2-orpo.Q4_K.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q4_K.gguf) | Q4_K | 0.11GB |\n| [HW2-orpo.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q4_K_M.gguf) | Q4_K_M | 0.11GB |\n| [HW2-orpo.Q4_1.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q4_1.gguf) | Q4_1 | 0.11GB |\n| [HW2-orpo.Q5_0.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q5_0.gguf) | Q5_0 | 0.11GB |\n| [HW2-orpo.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q5_K_S.gguf) | Q5_K_S | 0.11GB |\n| [HW2-orpo.Q5_K.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q5_K.gguf) | Q5_K | 0.12GB |\n| [HW2-orpo.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q5_K_M.gguf) | Q5_K_M | 0.12GB |\n| [HW2-orpo.Q5_1.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q5_1.gguf) | Q5_1 | 0.12GB |\n| [HW2-orpo.Q6_K.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q6_K.gguf) | Q6_K | 0.13GB |\n| [HW2-orpo.Q8_0.gguf](https://huggingface.co/RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf/blob/main/HW2-orpo.Q8_0.gguf) | Q8_0 | 0.17GB |\n\n\n\n\nOriginal model description:\n---\r\nlibrary_name: transformers\r\nlicense: mit\r\nbase_model: openai-community/gpt2\r\ntags:\r\n- trl\r\n- orpo\r\n- generated_from_trainer\r\ndatasets:\r\n- piqa\r\nmodel-index:\r\n- name: HW2-orpo\r\n  results: []\r\n---\r\n\r\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\r\nshould probably proofread and complete it, then remove this comment. -->\r\n\r\n# HW2-orpo\r\n\r\nThis model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the piqa dataset.\r\nIt achieves the following results on the evaluation set:\r\n- Loss: 3.8617\r\n- Rewards/chosen: -0.3716\r\n- Rewards/rejected: -0.3885\r\n- Rewards/accuracies: 0.6390\r\n- Rewards/margins: 0.0170\r\n- Logps/rejected: -3.8851\r\n- Logps/chosen: -3.7156\r\n- Logits/rejected: -3.3968\r\n- Logits/chosen: -3.5059\r\n- Nll Loss: 3.7885\r\n- Log Odds Ratio: -0.7324\r\n- Log Odds Chosen: 0.1830\r\n\r\n## Model description\r\n\r\nMore information needed\r\n\r\n## Intended uses & limitations\r\n\r\nMore information needed\r\n\r\n## Training and evaluation data\r\n\r\nMore information needed\r\n\r\n## Training procedure\r\n\r\n### Training hyperparameters\r\n\r\nThe following hyperparameters were used during training:\r\n- learning_rate: 5e-05\r\n- train_batch_size: 1\r\n- eval_batch_size: 1\r\n- seed: 42\r\n- gradient_accumulation_steps: 8\r\n- total_train_batch_size: 8\r\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\r\n- lr_scheduler_type: linear\r\n- num_epochs: 5\r\n- mixed_precision_training: Native AMP\r\n\r\n### Training results\r\n\r\n| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |\r\n|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|\r\n| 3.5511        | 0.2758 | 500  | 3.4162          | -0.3146        | -0.3224          | 0.6303             | 0.0078          | -3.2238        | -3.1457      | -12.1919        | -12.3316      | 3.3464   | -0.6978        | 0.0837          |\r\n| 3.3852        | 0.5517 | 1000 | 3.3345          | -0.3060        | -0.3152          | 0.6421             | 0.0092          | -3.1517        | -3.0602      | -3.3351         | -3.5024       | 3.2656   | -0.6894        | 0.0984          |\r\n| 3.2734        | 0.8275 | 1500 | 3.2903          | -0.3011        | -0.3101          | 0.6309             | 0.0090          | -3.1013        | -3.0113      | -5.6602         | -5.7320       | 3.2211   | -0.6920        | 0.0975          |\r\n| 3.104         | 1.1034 | 2000 | 3.2933          | -0.3021        | -0.3118          | 0.6371             | 0.0097          | -3.1182        | -3.0211      | -0.2253         | -0.3135       | 3.2237   | -0.6956        | 0.1062          |\r\n| 2.8138        | 1.3792 | 2500 | 3.2816          | -0.3018        | -0.3125          | 0.6464             | 0.0107          | -3.1253        | -3.0179      | 1.3216          | 1.2346        | 3.2125   | -0.6916        | 0.1172          |\r\n| 2.8178        | 1.6551 | 3000 | 3.2660          | -0.2998        | -0.3108          | 0.6383             | 0.0109          | -3.1080        | -2.9985      | -0.7475         | -0.8064       | 3.1968   | -0.6923        | 0.1204          |\r\n| 2.8122        | 1.9309 | 3500 | 3.2586          | -0.2992        | -0.3104          | 0.6433             | 0.0112          | -3.1039        | -2.9922      | -2.8285         | -2.9509       | 3.1893   | -0.6925        | 0.1228          |\r\n| 2.4931        | 2.2067 | 4000 | 3.3765          | -0.3130        | -0.3256          | 0.6427             | 0.0127          | -3.2563        | -3.1296      | 1.6707          | 1.5380        | 3.3063   | -0.7020        | 0.1392          |\r\n| 2.3999        | 2.4826 | 4500 | 3.4109          | -0.3174        | -0.3298          | 0.6402             | 0.0125          | -3.2982        | -3.1736      | 1.4695          | 1.2634        | 3.3402   | -0.7069        | 0.1373          |\r\n| 2.4254        | 2.7584 | 5000 | 3.3882          | -0.3150        | -0.3278          | 0.6439             | 0.0128          | -3.2781        | -3.1497      | 2.1282          | 1.9044        | 3.3180   | -0.7018        | 0.1416          |\r\n| 2.373         | 3.0343 | 5500 | 3.5698          | -0.3370        | -0.3515          | 0.6408             | 0.0145          | -3.5149        | -3.3698      | 3.7150          | 3.6601        | 3.4983   | -0.7147        | 0.1595          |\r\n| 2.0541        | 3.3101 | 6000 | 3.6256          | -0.3430        | -0.3570          | 0.6284             | 0.0140          | -3.5700        | -3.4302      | 1.1269          | 0.9714        | 3.5532   | -0.7240        | 0.1540          |\r\n| 2.0641        | 3.5860 | 6500 | 3.6157          | -0.3425        | -0.3577          | 0.6445             | 0.0152          | -3.5771        | -3.4246      | -0.6703         | -0.8165       | 3.5439   | -0.7178        | 0.1665          |\r\n| 2.0747        | 3.8618 | 7000 | 3.6335          | -0.3447        | -0.3598          | 0.6402             | 0.0151          | -3.5983        | -3.4474      | -0.1967         | -0.3291       | 3.5616   | -0.7193        | 0.1640          |\r\n| 1.9377        | 4.1376 | 7500 | 3.8286          | -0.3671        | -0.3838          | 0.6445             | 0.0167          | -3.8381        | -3.6712      | -2.6871         | -2.8058       | 3.7557   | -0.7288        | 0.1800          |\r\n| 1.8001        | 4.4135 | 8000 | 3.8629          | -0.3715        | -0.3882          | 0.6414             | 0.0168          | -3.8822        | -3.7146      | -3.4193         | -3.5370       | 3.7898   | -0.7315        | 0.1810          |\r\n| 1.81          | 4.6893 | 8500 | 3.8574          | -0.3711        | -0.3879          | 0.6396             | 0.0168          | -3.8789        | -3.7110      | -4.2176         | -4.3406       | 3.7842   | -0.7321        | 0.1814          |\r\n| 1.8108        | 4.9652 | 9000 | 3.8617          | -0.3716        | -0.3885          | 0.6390             | 0.0170          | -3.8851        | -3.7156      | -3.3968         | -3.5059       | 3.7885   | -0.7324        | 0.1830          |\r\n\r\n\r\n### Framework versions\r\n\r\n- Transformers 4.44.2\r\n- Pytorch 2.4.0+cu118\r\n- Datasets 2.21.0\r\n- Tokenizers 0.19.1\r\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 262,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-19T07:41:54.000Z",
  "created_at": "2025-03-19T07:38:37.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67da747dc42d3251c0677568",
  "id": "RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf",
  "modelId": "RichardErkhov/KoNqUeRoR3891_-_HW2-orpo-gguf",
  "sha": "27d79a7a2fb668e81d5ef56bb9f05919768926c8",
  "createdAt": "2025-03-19T07:38:37.000Z",
  "lastModified": "2025-03-19T07:41:54.000Z",
  "author": "RichardErkhov",
  "downloads": 262,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}