afrideva/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1",
    "datasets": [
      "OpenAssistant/oasst_top1_2023-08-25"
    ],
    "inference": false,
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "model_creator": "habanoz",
    "model_name": "TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1",
    "pipeline_tag": "text-generation",
    "quantized_by": "afrideva",
    "tags": [
      "gguf",
      "ggml",
      "quantized",
      "q2_k",
      "q3_k_m",
      "q4_k_m",
      "q5_k_m",
      "q6_k",
      "q8_0"
    ],
    "frontmatter": {
      "base_model": "habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1",
      "datasets": [
        "OpenAssistant/oasst_top1_2023-08-25"
      ],
      "inference": "false",
      "language": [
        "en"
      ],
      "license": "apache-2.0",
      "model_creator": "habanoz",
      "model_name": "TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1",
      "pipeline_tag": "text-generation",
      "quantized_by": "afrideva",
      "tags": [
        "gguf",
        "ggml",
        "quantized",
        "q2_k",
        "q3_k_m",
        "q4_k_m",
        "q5_k_m",
        "q6_k",
        "q8_0"
      ]
    },
    "hero_image_url": "",
    "summary": "# habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF Quantized GGUF model files for TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1 from habanoz | Name | Quant method | Size | | ---- | ---- | ---- | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.fp16.gguf | fp16 | 2.20 GB  | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q2_k.gguf | q2_k | 483.12 MB  | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q3_k_m.gguf | q3_k_m | 550.82 MB  | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q4_k_m.gguf | q4_k_m | 668.79 MB  | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q5_k_m.gguf | q5_k_m | 783.02 MB  | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q6_k.gguf | q6_k | 904.39 MB  | | tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q8_0.gguf | q8_0 | 1.17 GB  |",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1\ndatasets:\n- OpenAssistant/oasst_top1_2023-08-25\ninference: false\nlanguage:\n- en\nlicense: apache-2.0\nmodel_creator: habanoz\nmodel_name: TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1\npipeline_tag: text-generation\nquantized_by: afrideva\ntags:\n- gguf\n- ggml\n- quantized\n- q2_k\n- q3_k_m\n- q4_k_m\n- q5_k_m\n- q6_k\n- q8_0\n---\n# habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF\n\nQuantized GGUF model files for [TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1](https://huggingface.co/habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1) from [habanoz](https://huggingface.co/habanoz)\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.fp16.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.fp16.gguf) | fp16 | 2.20 GB  |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q2_k.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q2_k.gguf) | q2_k | 483.12 MB  |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q3_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q3_k_m.gguf) | q3_k_m | 550.82 MB  |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q4_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q4_k_m.gguf) | q4_k_m | 668.79 MB  |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q5_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q5_k_m.gguf) | q5_k_m | 783.02 MB  |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q6_k.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q6_k.gguf) | q6_k | 904.39 MB  |\n| [tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q8_0.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF/resolve/main/tinyllama-1.1b-step-2t-lr-5-5ep-oasst1-top1-instruct-v1.q8_0.gguf) | q8_0 | 1.17 GB  |\n\n\n\n## Original Model Card:\nTinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T finetuned using OpenAssistant/oasst_top1_2023-08-25 dataset. \n\nTrained for 5 epochs using Qlora. Adapter is merged.\n\nSFT code:\nhttps://github.com/habanoz/qlora.git\n\nCommand used:\n```bash\naccelerate launch $BASE_DIR/qlora/train.py \\\n  --model_name_or_path $BASE_MODEL \\\n  --working_dir $BASE_DIR/$OUTPUT_NAME-checkpoints \\\n  --output_dir $BASE_DIR/$OUTPUT_NAME-peft \\\n  --merged_output_dir $BASE_DIR/$OUTPUT_NAME \\\n  --final_output_dir $BASE_DIR/$OUTPUT_NAME-final \\\n  --num_train_epochs 5 \\\n  --logging_steps 1 \\\n  --save_strategy steps \\\n  --save_steps 75 \\\n  --save_total_limit 2 \\\n  --data_seed 11422 \\\n  --evaluation_strategy steps \\\n  --per_device_eval_batch_size 4 \\\n  --eval_dataset_size 0.01 \\\n  --eval_steps 75 \\\n  --max_new_tokens 1024 \\\n  --dataloader_num_workers 3 \\\n  --logging_strategy steps \\\n  --do_train \\\n  --do_eval \\\n  --lora_r 64 \\\n  --lora_alpha 16 \\\n  --lora_modules all \\\n  --bits 4 \\\n  --double_quant \\\n  --quant_type nf4 \\\n  --lr_scheduler_type constant \\\n  --dataset oasst1-top1 \\\n  --dataset_format oasst1 \\\n  --model_max_len 1024 \\\n  --per_device_train_batch_size 4 \\\n  --gradient_accumulation_steps 4 \\\n  --learning_rate 1e-5 \\\n  --adam_beta2 0.999 \\\n  --max_grad_norm 0.3 \\\n  --lora_dropout 0.0 \\\n  --weight_decay 0.0 \\\n  --seed 11422 \\\n  --gradient_checkpointing \\\n  --use_flash_attention_2 \\\n  --ddp_find_unused_parameters False\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "ggml",
    "quantized",
    "q2_k",
    "q3_k_m",
    "q4_k_m",
    "q5_k_m",
    "q6_k",
    "q8_0",
    "text-generation",
    "en",
    "dataset:OpenAssistant/oasst_top1_2023-08-25",
    "base_model:habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1",
    "base_model:quantized:habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1",
    "license:apache-2.0",
    "region:us"
  ],
  "likes": 0,
  "downloads": 87,
  "gated": false,
  "private": false,
  "last_modified": "2023-11-28T14:13:49.000Z",
  "created_at": "2023-11-28T14:09:29.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "6565f49977d8a948ac5935c3",
  "id": "afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF",
  "modelId": "afrideva/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-GGUF",
  "sha": "e930ecd57997df12b110e3ab66ff3a5038bbc746",
  "createdAt": "2023-11-28T14:09:29.000Z",
  "lastModified": "2023-11-28T14:13:49.000Z",
  "author": "afrideva",
  "downloads": 87,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 9
}