richarderkhov/habanoz_-_tinyllama-1.1b-intermediate-step-715k-1.5t-lr-5-3epochs-oasst1-top1-instruct-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Detailed results can be found here |             Metric              |Value| |---------------------------------|----:| |Avg.                             |35.42| |AI2 Reasoning Challenge (25-Shot)|31.40| |HellaSwag (10-Shot)              |54.24| |MMLU (5-Shot)                    |25.36| |TruthfulQA (0-shot)              |42.47| |Winogrande (5-shot)              |57.70| |GSM8k (5-shot)                   | 1.36|",
    "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\nTinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1 - GGUF\n- Model creator: https://huggingface.co/habanoz/\n- Original model: https://huggingface.co/habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q2_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q2_K.gguf) | Q2_K | 0.4GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ3_XS.gguf) | IQ3_XS | 0.44GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ3_S.gguf) | IQ3_S | 0.47GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K_S.gguf) | Q3_K_S | 0.47GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ3_M.gguf) | IQ3_M | 0.48GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K.gguf) | Q3_K | 0.51GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K_M.gguf) | Q3_K_M | 0.51GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q3_K_L.gguf) | Q3_K_L | 0.55GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ4_XS.gguf) | IQ4_XS | 0.57GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_0.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_0.gguf) | Q4_0 | 0.59GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.IQ4_NL.gguf) | IQ4_NL | 0.6GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_K_S.gguf) | Q4_K_S | 0.6GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_K.gguf) | Q4_K | 0.62GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_K_M.gguf) | Q4_K_M | 0.62GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_1.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q4_1.gguf) | Q4_1 | 0.65GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_0.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_0.gguf) | Q5_0 | 0.71GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_K_S.gguf) | Q5_K_S | 0.71GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_K.gguf) | Q5_K | 0.73GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_K_M.gguf) | Q5_K_M | 0.73GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_1.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q5_1.gguf) | Q5_1 | 0.77GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q6_K.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q6_K.gguf) | Q6_K | 0.84GB |\n| [TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q8_0.gguf](https://huggingface.co/RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf/blob/main/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1.Q8_0.gguf) | Q8_0 | 1.09GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- en\nlicense: apache-2.0\ndatasets:\n- OpenAssistant/oasst_top1_2023-08-25\npipeline_tag: text-generation\nmodel-index:\n- name: TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: AI2 Reasoning Challenge (25-Shot)\n      type: ai2_arc\n      config: ARC-Challenge\n      split: test\n      args:\n        num_few_shot: 25\n    metrics:\n    - type: acc_norm\n      value: 31.4\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: HellaSwag (10-Shot)\n      type: hellaswag\n      split: validation\n      args:\n        num_few_shot: 10\n    metrics:\n    - type: acc_norm\n      value: 54.24\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU (5-Shot)\n      type: cais/mmlu\n      config: all\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 25.36\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: TruthfulQA (0-shot)\n      type: truthful_qa\n      config: multiple_choice\n      split: validation\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: mc2\n      value: 42.47\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: Winogrande (5-shot)\n      type: winogrande\n      config: winogrande_xl\n      split: validation\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 57.7\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GSM8k (5-shot)\n      type: gsm8k\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 1.36\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1\n      name: Open LLM Leaderboard\n---\n\nTinyLlama-1.1B-intermediate-step-715k-1.5T finetuned using OpenAssistant/oasst_top1_2023-08-25 dataset. \n\nQlora is used. 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 3 \\\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```\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_habanoz__TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |35.42|\n|AI2 Reasoning Challenge (25-Shot)|31.40|\n|HellaSwag (10-Shot)              |54.24|\n|MMLU (5-Shot)                    |25.36|\n|TruthfulQA (0-shot)              |42.47|\n|Winogrande (5-shot)              |57.70|\n|GSM8k (5-shot)                   | 1.36|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 126,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-24T21:30:03.000Z",
  "created_at": "2024-06-24T21:22:14.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6679e386eb164e55848f895d",
  "id": "RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf",
  "modelId": "RichardErkhov/habanoz_-_TinyLlama-1.1B-intermediate-step-715k-1.5T-lr-5-3epochs-oasst1-top1-instruct-V1-gguf",
  "sha": "6e89e48d880a027b2a81af76a6569747c280ae00",
  "createdAt": "2024-06-24T21:22:14.000Z",
  "lastModified": "2024-06-24T21:30:03.000Z",
  "author": "RichardErkhov",
  "downloads": 126,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}