richarderkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full 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\nzephyr-7b-ultra-p-0.02 - GGUF\n- Model creator: https://huggingface.co/tongliuphysics/\n- Original model: https://huggingface.co/tongliuphysics/zephyr-7b-ultra-p-0.02/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [zephyr-7b-ultra-p-0.02.Q2_K.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q2_K.gguf) | Q2_K | 2.53GB |\n| [zephyr-7b-ultra-p-0.02.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [zephyr-7b-ultra-p-0.02.IQ3_S.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [zephyr-7b-ultra-p-0.02.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [zephyr-7b-ultra-p-0.02.IQ3_M.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [zephyr-7b-ultra-p-0.02.Q3_K.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q3_K.gguf) | Q3_K | 3.28GB |\n| [zephyr-7b-ultra-p-0.02.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [zephyr-7b-ultra-p-0.02.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [zephyr-7b-ultra-p-0.02.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [zephyr-7b-ultra-p-0.02.Q4_0.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [zephyr-7b-ultra-p-0.02.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [zephyr-7b-ultra-p-0.02.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [zephyr-7b-ultra-p-0.02.Q4_K.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q4_K.gguf) | Q4_K | 4.07GB |\n| [zephyr-7b-ultra-p-0.02.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [zephyr-7b-ultra-p-0.02.Q4_1.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [zephyr-7b-ultra-p-0.02.Q5_0.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [zephyr-7b-ultra-p-0.02.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [zephyr-7b-ultra-p-0.02.Q5_K.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q5_K.gguf) | Q5_K | 4.78GB |\n| [zephyr-7b-ultra-p-0.02.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [zephyr-7b-ultra-p-0.02.Q5_1.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [zephyr-7b-ultra-p-0.02.Q6_K.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q6_K.gguf) | Q6_K | 5.53GB |\n| [zephyr-7b-ultra-p-0.02.Q8_0.gguf](https://huggingface.co/RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf/blob/main/zephyr-7b-ultra-p-0.02.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: apache-2.0\nbase_model: alignment-handbook/zephyr-7b-sft-full\ntags:\n- trl\n- dpo\n- generated_from_trainer\nmodel-index:\n- name: zephyr-7b-ultra-p-0.02\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# zephyr-7b-ultra-p-0.02\n\nThis model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5105\n- Rewards/chosen: -0.5077\n- Rewards/rejected: -2.0215\n- Rewards/accuracies: 0.7344\n- Rewards/margins: 1.5138\n- Logps/rejected: -267.6940\n- Logps/chosen: -235.0849\n- Logits/rejected: -2.5635\n- Logits/chosen: -2.6281\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-07\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 8\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: linear\n- num_epochs: 1.0\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |\n|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|\n| 0.5874        | 0.1030 | 100  | 0.5573          | -0.2314        | -0.8600          | 0.6797             | 0.6286          | -256.0786      | -232.3214    | -2.5790         | -2.6440       |\n| 0.5473        | 0.2060 | 200  | 0.5392          | -0.5176        | -1.5117          | 0.7031             | 0.9941          | -262.5964      | -235.1839    | -2.5004         | -2.5620       |\n| 0.5436        | 0.3090 | 300  | 0.5426          | -0.5160        | -1.3998          | 0.6797             | 0.8838          | -261.4774      | -235.1676    | -2.5184         | -2.5855       |\n| 0.5247        | 0.4120 | 400  | 0.5351          | -0.6497        | -2.2938          | 0.7422             | 1.6441          | -270.4168      | -236.5049    | -2.5925         | -2.6552       |\n| 0.5168        | 0.5150 | 500  | 0.5223          | -0.3770        | -1.8625          | 0.6875             | 1.4854          | -266.1038      | -233.7780    | -2.5839         | -2.6438       |\n| 0.5123        | 0.6180 | 600  | 0.5238          | -0.3471        | -1.8780          | 0.7344             | 1.5310          | -266.2595      | -233.4782    | -2.5479         | -2.6121       |\n| 0.5266        | 0.7210 | 700  | 0.5222          | -0.3742        | -1.8507          | 0.7109             | 1.4765          | -265.9860      | -233.7501    | -2.5703         | -2.6311       |\n| 0.5395        | 0.8240 | 800  | 0.5190          | -0.4812        | -2.0133          | 0.7266             | 1.5321          | -267.6115      | -234.8195    | -2.5854         | -2.6511       |\n| 0.4871        | 0.9270 | 900  | 0.5121          | -0.4722        | -1.9692          | 0.7109             | 1.4969          | -267.1705      | -234.7301    | -2.5606         | -2.6256       |\n\n\n### Framework versions\n\n- Transformers 4.45.1\n- Pytorch 2.4.1+cu121\n- Datasets 3.0.0\n- Tokenizers 0.20.0\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 170,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-15T00:53:13.000Z",
  "created_at": "2025-04-14T23:13:33.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67fd969da77dcced6ad5bffa",
  "id": "RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf",
  "modelId": "RichardErkhov/tongliuphysics_-_zephyr-7b-ultra-p-0.02-gguf",
  "sha": "9a57ac225a18d00b2a1e378dea812a03b3d1a5dc",
  "createdAt": "2025-04-14T23:13:33.000Z",
  "lastModified": "2025-04-15T00:53:13.000Z",
  "author": "RichardErkhov",
  "downloads": 170,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}