richarderkhov/charlesli_-_openelm-1_1b-ipo-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model was trained from scratch 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\nOpenELM-1_1B-IPO - GGUF\n- Model creator: https://huggingface.co/CharlesLi/\n- Original model: https://huggingface.co/CharlesLi/OpenELM-1_1B-IPO/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [OpenELM-1_1B-IPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q2_K.gguf) | Q2_K | 0.39GB |\n| [OpenELM-1_1B-IPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.IQ3_XS.gguf) | IQ3_XS | 0.44GB |\n| [OpenELM-1_1B-IPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.IQ3_S.gguf) | IQ3_S | 0.46GB |\n| [OpenELM-1_1B-IPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q3_K_S.gguf) | Q3_K_S | 0.46GB |\n| [OpenELM-1_1B-IPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.IQ3_M.gguf) | IQ3_M | 0.49GB |\n| [OpenELM-1_1B-IPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q3_K.gguf) | Q3_K | 0.52GB |\n| [OpenELM-1_1B-IPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q3_K_M.gguf) | Q3_K_M | 0.52GB |\n| [OpenELM-1_1B-IPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q3_K_L.gguf) | Q3_K_L | 0.56GB |\n| [OpenELM-1_1B-IPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.IQ4_XS.gguf) | IQ4_XS | 0.55GB |\n| [OpenELM-1_1B-IPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q4_0.gguf) | Q4_0 | 0.58GB |\n| [OpenELM-1_1B-IPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.IQ4_NL.gguf) | IQ4_NL | 0.58GB |\n| [OpenELM-1_1B-IPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q4_K_S.gguf) | Q4_K_S | 0.58GB |\n| [OpenELM-1_1B-IPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q4_K.gguf) | Q4_K | 0.63GB |\n| [OpenELM-1_1B-IPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q4_K_M.gguf) | Q4_K_M | 0.63GB |\n| [OpenELM-1_1B-IPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q4_1.gguf) | Q4_1 | 0.64GB |\n| [OpenELM-1_1B-IPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q5_0.gguf) | Q5_0 | 0.7GB |\n| [OpenELM-1_1B-IPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q5_K_S.gguf) | Q5_K_S | 0.7GB |\n| [OpenELM-1_1B-IPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q5_K.gguf) | Q5_K | 0.73GB |\n| [OpenELM-1_1B-IPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q5_K_M.gguf) | Q5_K_M | 0.73GB |\n| [OpenELM-1_1B-IPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q5_1.gguf) | Q5_1 | 0.76GB |\n| [OpenELM-1_1B-IPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q6_K.gguf) | Q6_K | 0.83GB |\n| [OpenELM-1_1B-IPO.Q8_0.gguf](https://huggingface.co/RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf/blob/main/OpenELM-1_1B-IPO.Q8_0.gguf) | Q8_0 | 1.07GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\ntags:\n- trl\n- dpo\n- alignment-handbook\n- generated_from_trainer\nmodel-index:\n- name: OpenELM-1_1B-IPO\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# OpenELM-1_1B-IPO\n\nThis model was trained from scratch on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Logits/chosen: -0.6367\n- Logits/rejected: 0.8008\n- Logps/chosen: -49.75\n- Logps/rejected: -62.75\n- Loss: 1943.3600\n- Rewards/accuracies: 0.6953\n- Rewards/chosen: -0.4863\n- Rewards/margins: 0.1309\n- Rewards/rejected: -0.6172\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: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 16\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 3\n\n### Training results\n\n| Training Loss | Epoch  | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |\n|:-------------:|:------:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|\n| 2322.6        | 0.1047 | 100  | -8.875        | -8.375          | -13.1875     | -15.875        | 2317.6321       | 0.625              | -0.1211        | 0.0258          | -0.1465          |\n| 2118.6        | 0.2093 | 200  | -10.125       | -9.75           | -30.5        | -37.25         | 2150.9761       | 0.6738             | -0.2930        | 0.0664          | -0.3594          |\n| 2172.1        | 0.3140 | 300  | -8.4375       | -7.8438         | -37.0        | -44.0          | 2062.5920       | 0.6895             | -0.3594        | 0.0674          | -0.4277          |\n| 2039.3        | 0.4186 | 400  | -6.0938       | -5.4375         | -28.5        | -37.0          | 1999.0400       | 0.6914             | -0.2734        | 0.0850          | -0.3594          |\n| 1938.55       | 0.5233 | 500  | -6.2812       | -5.25           | -40.0        | -51.25         | 1975.6801       | 0.6953             | -0.3906        | 0.1113          | -0.5             |\n| 1949.6        | 0.6279 | 600  | -6.3438       | -4.9062         | -34.5        | -44.0          | 1962.8800       | 0.7051             | -0.3340        | 0.0942          | -0.4277          |\n| 1951.75       | 0.7326 | 700  | -8.6875       | -7.0625         | -30.625      | -41.25         | 1956.0959       | 0.7090             | -0.2949        | 0.1055          | -0.4004          |\n| 1869.7        | 0.8373 | 800  | -1.2031       | 0.3184          | -37.0        | -48.75         | 1889.7280       | 0.7207             | -0.3594        | 0.1147          | -0.4746          |\n| 1905.45       | 0.9419 | 900  | -6.0625       | -4.2188         | -42.5        | -54.25         | 1903.8400       | 0.7070             | -0.4141        | 0.1167          | -0.5312          |\n| 1301.1        | 1.0466 | 1000 | -0.8906       | 0.2236          | -40.0        | -54.25         | 1946.8480       | 0.7109             | -0.3887        | 0.1416          | -0.5312          |\n| 1193.05       | 1.1512 | 1100 | -1.6094       | -0.3926         | -45.0        | -59.25         | 1939.2321       | 0.7031             | -0.4395        | 0.1406          | -0.5781          |\n| 1162.575      | 1.2559 | 1200 | -2.0938       | -0.7109         | -45.5        | -59.75         | 1908.4800       | 0.7070             | -0.4434        | 0.1406          | -0.5859          |\n| 1153.3        | 1.3605 | 1300 | -2.8281       | -1.3594         | -41.25       | -54.75         | 1974.0800       | 0.6973             | -0.4004        | 0.1357          | -0.5352          |\n| 1084.875      | 1.4652 | 1400 | -1.5078       | 0.0021          | -48.0        | -61.5          | 1926.9440       | 0.7051             | -0.4688        | 0.1338          | -0.6016          |\n| 1031.2313     | 1.5699 | 1500 | -1.6641       | -0.1064         | -42.0        | -56.75         | 1931.5840       | 0.7031             | -0.4082        | 0.1465          | -0.5547          |\n| 1090.75       | 1.6745 | 1600 | -1.375        | 0.0486          | -44.25       | -58.25         | 1936.1281       | 0.6973             | -0.4316        | 0.1396          | -0.5703          |\n| 1097.5375     | 1.7792 | 1700 | -2.2344       | -0.6602         | -47.5        | -62.0          | 1975.2960       | 0.7070             | -0.4648        | 0.1445          | -0.6094          |\n| 1031.15       | 1.8838 | 1800 | -0.8125       | 0.4512          | -48.0        | -62.25         | 1964.5120       | 0.7090             | -0.4668        | 0.1416          | -0.6094          |\n| 1012.0125     | 1.9885 | 1900 | -0.7578       | 0.6133          | -46.25       | -60.25         | 1937.0240       | 0.7031             | -0.4512        | 0.1406          | -0.5898          |\n| 262.0437      | 2.0931 | 2000 | -0.875        | 0.5430          | -47.75       | -60.75         | 1950.9440       | 0.6895             | -0.4668        | 0.1309          | -0.5977          |\n| 266.8375      | 2.1978 | 2100 | -1.25         | 0.2207          | -47.25       | -60.25         | 1943.8719       | 0.7090             | -0.4609        | 0.1279          | -0.5898          |\n| 284.8125      | 2.3025 | 2200 | -0.5508       | 0.8164          | -49.75       | -62.75         | 1946.7520       | 0.6934             | -0.4883        | 0.1289          | -0.6172          |\n| 303.8625      | 2.4071 | 2300 | -0.4082       | 0.9297          | -50.25       | -63.0          | 1945.9840       | 0.6973             | -0.4902        | 0.1279          | -0.6172          |\n| 266.5266      | 2.5118 | 2400 | -0.6602       | 0.7578          | -49.25       | -62.25         | 1952.0640       | 0.6914             | -0.4805        | 0.1289          | -0.6094          |\n| 220.4344      | 2.6164 | 2500 | -0.5625       | 0.8672          | -49.25       | -62.25         | 1944.1281       | 0.6973             | -0.4805        | 0.1309          | -0.6094          |\n| 253.4812      | 2.7211 | 2600 | -0.5469       | 0.8789          | -50.0        | -63.0          | 1938.1121       | 0.6914             | -0.4883        | 0.1299          | -0.6172          |\n| 271.3984      | 2.8257 | 2700 | -0.6328       | 0.8047          | -49.75       | -63.0          | 1943.8719       | 0.6953             | -0.4863        | 0.1299          | -0.6172          |\n| 292.8133      | 2.9304 | 2800 | -0.6367       | 0.8008          | -49.75       | -62.75         | 1943.3600       | 0.6953             | -0.4863        | 0.1309          | -0.6172          |\n\n\n### Framework versions\n\n- Transformers 4.44.2\n- Pytorch 2.3.0\n- Datasets 3.0.0\n- Tokenizers 0.19.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 230,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-01T13:38:45.000Z",
  "created_at": "2025-04-01T13:23:21.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67ebe8c9080ab23783e17502",
  "id": "RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf",
  "modelId": "RichardErkhov/CharlesLi_-_OpenELM-1_1B-IPO-gguf",
  "sha": "1f5e5a6af0a7d8bc47cb208be29236cb5e6fd951",
  "createdAt": "2025-04-01T13:23:21.000Z",
  "lastModified": "2025-04-01T13:38:45.000Z",
  "author": "RichardErkhov",
  "downloads": 230,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}