richarderkhov/kykim0_-_llama-2-7b-ultrachat-syn-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "# - HuggingFaceH4/ultrachat_200k model-index: results: [] ---  # Llama-2-7b-ultrachat-syn <!-- This model is a fine-tuned version of kykim0/Llama-2-7b-ultrachat200k-2e on the HuggingFaceH4/ultrachat_200k 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\nLlama-2-7b-ultrachat-syn - GGUF\n- Model creator: https://huggingface.co/kykim0/\n- Original model: https://huggingface.co/kykim0/Llama-2-7b-ultrachat-syn/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-2-7b-ultrachat-syn.Q2_K.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q2_K.gguf) | Q2_K | 2.36GB |\n| [Llama-2-7b-ultrachat-syn.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.IQ3_XS.gguf) | IQ3_XS | 2.6GB |\n| [Llama-2-7b-ultrachat-syn.IQ3_S.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.IQ3_S.gguf) | IQ3_S | 2.75GB |\n| [Llama-2-7b-ultrachat-syn.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q3_K_S.gguf) | Q3_K_S | 2.75GB |\n| [Llama-2-7b-ultrachat-syn.IQ3_M.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.IQ3_M.gguf) | IQ3_M | 2.9GB |\n| [Llama-2-7b-ultrachat-syn.Q3_K.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q3_K.gguf) | Q3_K | 3.07GB |\n| [Llama-2-7b-ultrachat-syn.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q3_K_M.gguf) | Q3_K_M | 3.07GB |\n| [Llama-2-7b-ultrachat-syn.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q3_K_L.gguf) | Q3_K_L | 3.35GB |\n| [Llama-2-7b-ultrachat-syn.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.IQ4_XS.gguf) | IQ4_XS | 3.4GB |\n| [Llama-2-7b-ultrachat-syn.Q4_0.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q4_0.gguf) | Q4_0 | 3.56GB |\n| [Llama-2-7b-ultrachat-syn.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.IQ4_NL.gguf) | IQ4_NL | 3.58GB |\n| [Llama-2-7b-ultrachat-syn.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q4_K_S.gguf) | Q4_K_S | 3.59GB |\n| [Llama-2-7b-ultrachat-syn.Q4_K.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q4_K.gguf) | Q4_K | 3.8GB |\n| [Llama-2-7b-ultrachat-syn.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q4_K_M.gguf) | Q4_K_M | 3.8GB |\n| [Llama-2-7b-ultrachat-syn.Q4_1.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q4_1.gguf) | Q4_1 | 3.95GB |\n| [Llama-2-7b-ultrachat-syn.Q5_0.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q5_0.gguf) | Q5_0 | 4.33GB |\n| [Llama-2-7b-ultrachat-syn.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q5_K_S.gguf) | Q5_K_S | 4.33GB |\n| [Llama-2-7b-ultrachat-syn.Q5_K.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q5_K.gguf) | Q5_K | 4.45GB |\n| [Llama-2-7b-ultrachat-syn.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q5_K_M.gguf) | Q5_K_M | 4.45GB |\n| [Llama-2-7b-ultrachat-syn.Q5_1.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q5_1.gguf) | Q5_1 | 4.72GB |\n| [Llama-2-7b-ultrachat-syn.Q6_K.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q6_K.gguf) | Q6_K | 5.15GB |\n| [Llama-2-7b-ultrachat-syn.Q8_0.gguf](https://huggingface.co/RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf/blob/main/Llama-2-7b-ultrachat-syn.Q8_0.gguf) | Q8_0 | 6.67GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nbase_model: kykim0/Llama-2-7b-ultrachat200k-2e\ntags:\n- alignment-handbook\n- trl\n- sft\n- generated_from_trainer\n- trl\n- sft\n- generated_from_trainer\n# datasets:\n# - HuggingFaceH4/ultrachat_200k\nmodel-index:\n- name: Llama-2-7b-ultrachat-syn\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# Llama-2-7b-ultrachat-syn\n\n<!-- This model is a fine-tuned version of [kykim0/Llama-2-7b-ultrachat200k-2e](https://huggingface.co/kykim0/Llama-2-7b-ultrachat200k-2e) on the HuggingFaceH4/ultrachat_200k dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.0863 -->\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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\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: 2\n\n### Training results\n\n<!-- | Training Loss | Epoch  | Step | Validation Loss |\n|:-------------:|:------:|:----:|:---------------:|\n| 0.0994        | 0.9984 | 156  | 0.0907          |\n| 0.0916        | 1.9968 | 312  | 0.0863          | -->\n\n\n### Framework versions\n\n- Transformers 4.44.2\n- Pytorch 2.1.2\n- Datasets 2.14.6\n- Tokenizers 0.19.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 82,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-19T23:40:19.000Z",
  "created_at": "2024-09-19T20:04:47.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66ec83df3b250e9eca1442cf",
  "id": "RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf",
  "modelId": "RichardErkhov/kykim0_-_Llama-2-7b-ultrachat-syn-gguf",
  "sha": "58b23ab4125548a8a03a813c25db3e0e8cf18b83",
  "createdAt": "2024-09-19T20:04:47.000Z",
  "lastModified": "2024-09-19T23:40:19.000Z",
  "author": "RichardErkhov",
  "downloads": 82,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}