richarderkhov/laislemke_-_llama-2-vicuna-7b-slerp-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "LLaMA-2-vicuna-7b-slerp is a merge of the following models using LazyMergekit: * togethercomputer/LLaMA-2-7B-32K * lmsys/vicuna-7b-v1.5",
    "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-vicuna-7b-slerp - GGUF\n- Model creator: https://huggingface.co/laislemke/\n- Original model: https://huggingface.co/laislemke/LLaMA-2-vicuna-7b-slerp/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [LLaMA-2-vicuna-7b-slerp.Q2_K.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q2_K.gguf) | Q2_K | 2.36GB |\n| [LLaMA-2-vicuna-7b-slerp.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.IQ3_XS.gguf) | IQ3_XS | 1.14GB |\n| [LLaMA-2-vicuna-7b-slerp.IQ3_S.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.IQ3_S.gguf) | IQ3_S | 0.71GB |\n| [LLaMA-2-vicuna-7b-slerp.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q3_K_S.gguf) | Q3_K_S | 2.75GB |\n| [LLaMA-2-vicuna-7b-slerp.IQ3_M.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.IQ3_M.gguf) | IQ3_M | 2.9GB |\n| [LLaMA-2-vicuna-7b-slerp.Q3_K.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q3_K.gguf) | Q3_K | 0.62GB |\n| [LLaMA-2-vicuna-7b-slerp.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q3_K_M.gguf) | Q3_K_M | 3.07GB |\n| [LLaMA-2-vicuna-7b-slerp.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q3_K_L.gguf) | Q3_K_L | 3.35GB |\n| [LLaMA-2-vicuna-7b-slerp.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.IQ4_XS.gguf) | IQ4_XS | 0.4GB |\n| [LLaMA-2-vicuna-7b-slerp.Q4_0.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q4_0.gguf) | Q4_0 | 0.27GB |\n| [LLaMA-2-vicuna-7b-slerp.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.IQ4_NL.gguf) | IQ4_NL | 0.1GB |\n| [LLaMA-2-vicuna-7b-slerp.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q4_K_S.gguf) | Q4_K_S | 0.88GB |\n| [LLaMA-2-vicuna-7b-slerp.Q4_K.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q4_K.gguf) | Q4_K | 0.28GB |\n| [LLaMA-2-vicuna-7b-slerp.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q4_K_M.gguf) | Q4_K_M | 0.53GB |\n| [LLaMA-2-vicuna-7b-slerp.Q4_1.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q4_1.gguf) | Q4_1 | 3.95GB |\n| [LLaMA-2-vicuna-7b-slerp.Q5_0.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q5_0.gguf) | Q5_0 | 4.33GB |\n| [LLaMA-2-vicuna-7b-slerp.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q5_K_S.gguf) | Q5_K_S | 3.3GB |\n| [LLaMA-2-vicuna-7b-slerp.Q5_K.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q5_K.gguf) | Q5_K | 2.22GB |\n| [LLaMA-2-vicuna-7b-slerp.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q5_K_M.gguf) | Q5_K_M | 0.6GB |\n| [LLaMA-2-vicuna-7b-slerp.Q5_1.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q5_1.gguf) | Q5_1 | 0.35GB |\n| [LLaMA-2-vicuna-7b-slerp.Q6_K.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q6_K.gguf) | Q6_K | 0.26GB |\n| [LLaMA-2-vicuna-7b-slerp.Q8_0.gguf](https://huggingface.co/RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf/blob/main/LLaMA-2-vicuna-7b-slerp.Q8_0.gguf) | Q8_0 | 0.2GB |\n\n\n\n\nOriginal model description:\n---\nbase_model:\n- togethercomputer/LLaMA-2-7B-32K\n- lmsys/vicuna-7b-v1.5\ntags:\n- merge\n- mergekit\n- lazymergekit\n- togethercomputer/LLaMA-2-7B-32K\n- lmsys/vicuna-7b-v1.5\nlicense: llama2\n---\n\n# LLaMA-2-vicuna-7b-slerp\n\nLLaMA-2-vicuna-7b-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):\n* [togethercomputer/LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K)\n* [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5)\n\n## 🧩 Configuration\n\n```yaml\nslices:\n  - sources:\n      - model: togethercomputer/LLaMA-2-7B-32K\n        layer_range: [0, 32]\n      - model: lmsys/vicuna-7b-v1.5\n        layer_range: [0, 32]\nmerge_method: slerp\nbase_model: togethercomputer/LLaMA-2-7B-32K\nparameters:\n  t:\n    - filter: self_attn\n      value: [0, 0.5, 0.3, 0.7, 1]\n    - filter: mlp\n      value: [1, 0.5, 0.7, 0.3, 0]\n    - value: 0.5\ndtype: bfloat16\n```\n\n## 💻 Usage\n\n```python\n!pip install -qU transformers accelerate\n\nfrom transformers import AutoTokenizer\nimport transformers\nimport torch\n\nmodel = \"laislemke/LLaMA-2-vicuna-7b-slerp\"\nmessages = [{\"role\": \"user\", \"content\": \"What is a large language model?\"}]\n\ntokenizer = AutoTokenizer.from_pretrained(model)\nprompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\npipeline = transformers.pipeline(\n    \"text-generation\",\n    model=model,\n    torch_dtype=torch.float16,\n    device_map=\"auto\",\n)\n\noutputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)\nprint(outputs[0][\"generated_text\"])\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 169,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-06T00:30:43.000Z",
  "created_at": "2024-08-05T23:48:32.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66b164d0d24408ea1804a920",
  "id": "RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf",
  "modelId": "RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf",
  "sha": "a646961c3c37469c2a2cfb1afcb4ae65e983bede",
  "createdAt": "2024-08-05T23:48:32.000Z",
  "lastModified": "2024-08-06T00:30:43.000Z",
  "author": "RichardErkhov",
  "downloads": 169,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}