richarderkhov/artificialguybr_-_meta-llama-3.1-8b-openhermes-2.5-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of Meta-Llama-3.1-8B on the OpenHermes-2.5 dataset.",
    "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\nMeta-Llama-3.1-8B-openhermes-2.5 - GGUF\n- Model creator: https://huggingface.co/artificialguybr/\n- Original model: https://huggingface.co/artificialguybr/Meta-Llama-3.1-8B-openhermes-2.5/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q2_K.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q2_K.gguf) | Q2_K | 2.96GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.IQ3_S.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.IQ3_M.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q3_K.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q3_K.gguf) | Q3_K | 3.74GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q4_0.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q4_K.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q4_K.gguf) | Q4_K | 4.58GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q4_1.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q5_0.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q5_K.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q5_K.gguf) | Q5_K | 5.34GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q5_1.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q6_K.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q6_K.gguf) | Q6_K | 6.14GB |\n| [Meta-Llama-3.1-8B-openhermes-2.5.Q8_0.gguf](https://huggingface.co/RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf/blob/main/Meta-Llama-3.1-8B-openhermes-2.5.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\ntags:\n  - llama\n  - instruct\n  - finetune\n  - chatml\n  - gpt4\n  - synthetic data\n  - distillation\nmodel-index:\n  - name: Meta-Llama-3.1-8B-openhermes-2.5\n    results: []\nlicense: apache-2.0\nlanguage:\n  - en\nlibrary_name: transformers\ndatasets:\n- teknium/OpenHermes-2.5\n---\n\n# Model Card for Meta-Llama-3.1-8B-openhermes-2.5\n\nThis model is a fine-tuned version of Meta-Llama-3.1-8B on the OpenHermes-2.5 dataset.\n\n## Model Details\n\n### Model Description\n\nThis is a fine-tuned version of the Meta-Llama-3.1-8B model, trained on the OpenHermes-2.5 dataset. It is designed for instruction following and general language tasks.\n\n- **Developed by:** artificialguybr\n- **Model type:** Causal Language Model\n- **Language(s):** English\n- **License:** apache-2.0\n- **Finetuned from model:** meta-llama/Meta-Llama-3.1-8B\n\n### Model Sources\n\n- **Repository:** https://huggingface.co/artificialguybr/Meta-Llama-3.1-8B-openhermes-2.5\n\n## Uses\n\nThis model can be used for various natural language processing tasks, particularly those involving instruction following and general language understanding.\n\n### Direct Use\n\nThe model can be used for tasks such as text generation, question answering, and other language-related applications.\n\n### Out-of-Scope Use\n\nThe model should not be used for generating harmful or biased content. Users should be aware of potential biases in the training data.\n\n## Training Details\n\n### Training Data\n\nThe model was fine-tuned on the teknium/OpenHermes-2.5 dataset.\n\n### Training Procedure\n\n#### Training Hyperparameters\n\n- **Training regime:** BF16 mixed precision\n- **Optimizer:** AdamW\n- **Learning rate:** Started at 0.00000249316296439037 (decaying)\n- **Batch size:** Not specified (gradient accumulation steps: 8)\n- **Training steps:** 13,368\n- **Evaluation strategy:** Steps (every 0.16666666666666666 steps)\n- **Gradient checkpointing:** Enabled\n- **Weight decay:** 0\n\n#### Hardware and Software\n\n- **Hardware:** NVIDIA A100-SXM4-80GB (1 GPU)\n- **Software Framework:** 🤗 Transformers, Axolotl\n\n## Evaluation\n\n### Metrics\n\n- **Loss:** 0.6727465987205505 (evaluation)\n- **Perplexity:** Not provided\n\n### Results\n\n- **Evaluation runtime:** 2,676.4173 seconds\n- **Samples per second:** 18.711\n- **Steps per second:** 18.711\n\n## Model Architecture\n\n- **Model Type:** LlamaForCausalLM\n- **Hidden size:** 4,096\n- **Intermediate size:** 14,336\n- **Number of attention heads:** Not specified\n- **Number of layers:** Not specified\n- **Activation function:** SiLU\n- **Vocabulary size:** 128,256\n\n## Limitations and Biases\n\nMore information is needed about specific limitations and biases of this model.\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 154,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-09T11:34:12.000Z",
  "created_at": "2024-08-09T10:08:49.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66b5eab172eda65b5e2388cf",
  "id": "RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf",
  "modelId": "RichardErkhov/artificialguybr_-_Meta-Llama-3.1-8B-openhermes-2.5-gguf",
  "sha": "cf21db1e5da9ebe7d19ed77ec8f8cf9c0f8af8cb",
  "createdAt": "2024-08-09T10:08:49.000Z",
  "lastModified": "2024-08-09T11:34:12.000Z",
  "author": "RichardErkhov",
  "downloads": 154,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}