richarderkhov/mcgill-nlp_-_sheared-llama-2.7b-weblinx-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "valid = load_dataset(\"McGill-NLP/weblinx\", split=\"validation\") # Download and load the templates snapshot_download( \"McGill-NLP/WebLINX\", repo_type=\"dataset\", allow_patterns=\"templates/*.txt\", local_dir=\"./\" ) with open('templates/llama.txt') as f: template = f.read() turn = valid[0] turn_text = template.format(**turn) # Load action model and input the text to get prediction action_model = pipeline( model=\"McGill-NLP/Sheared-LLaMA-2.7B-weblinx\", device=0, torch_dtype='auto' ) out = action_model(turn_text, return_full_text=False, max_new_tokens=64, truncation=True) pred = out[0]['generated_text'] print(\"Ref:\", turn[\"action\"]) print(\"Pred:\", pred) ```",
    "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\nSheared-LLaMA-2.7B-weblinx - GGUF\n- Model creator: https://huggingface.co/McGill-NLP/\n- Original model: https://huggingface.co/McGill-NLP/Sheared-LLaMA-2.7B-weblinx/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Sheared-LLaMA-2.7B-weblinx.Q2_K.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q2_K.gguf) | Q2_K | 0.96GB |\n| [Sheared-LLaMA-2.7B-weblinx.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.IQ3_XS.gguf) | IQ3_XS | 1.06GB |\n| [Sheared-LLaMA-2.7B-weblinx.IQ3_S.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.IQ3_S.gguf) | IQ3_S | 1.11GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q3_K_S.gguf) | Q3_K_S | 1.11GB |\n| [Sheared-LLaMA-2.7B-weblinx.IQ3_M.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.IQ3_M.gguf) | IQ3_M | 1.17GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q3_K.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q3_K.gguf) | Q3_K | 1.24GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q3_K_M.gguf) | Q3_K_M | 1.24GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q3_K_L.gguf) | Q3_K_L | 1.35GB |\n| [Sheared-LLaMA-2.7B-weblinx.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.IQ4_XS.gguf) | IQ4_XS | 1.37GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q4_0.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q4_0.gguf) | Q4_0 | 1.44GB |\n| [Sheared-LLaMA-2.7B-weblinx.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.IQ4_NL.gguf) | IQ4_NL | 1.44GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q4_K_S.gguf) | Q4_K_S | 1.45GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q4_K.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q4_K.gguf) | Q4_K | 1.53GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q4_K_M.gguf) | Q4_K_M | 1.53GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q4_1.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q4_1.gguf) | Q4_1 | 1.59GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q5_0.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q5_0.gguf) | Q5_0 | 1.74GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q5_K_S.gguf) | Q5_K_S | 1.74GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q5_K.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q5_K.gguf) | Q5_K | 1.79GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q5_K_M.gguf) | Q5_K_M | 1.79GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q5_1.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q5_1.gguf) | Q5_1 | 1.89GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q6_K.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q6_K.gguf) | Q6_K | 2.07GB |\n| [Sheared-LLaMA-2.7B-weblinx.Q8_0.gguf](https://huggingface.co/RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf/blob/main/Sheared-LLaMA-2.7B-weblinx.Q8_0.gguf) | Q8_0 | 2.67GB |\n\n\n\n\nOriginal model description:\n---\ndatasets:\n- McGill-NLP/WebLINX\n- McGill-NLP/WebLINX-full\nlanguage:\n- en\nmetrics:\n- f1\n- iou\n- chrf\nlibrary_name: transformers\npipeline_tag: text-generation\ntags:\n- weblinx\n- text-generation-inference\n- web-agents\n- agents\nlicense: llama2\n---\n<div align=\"center\">\n  <h1 style=\"margin-bottom: 0.5em;\">WebLINX: Real-World Website Navigation with Multi-Turn Dialogue</h1>\n  <em>Xing Han Lù*, Zdeněk Kasner*, Siva Reddy</em>\n</div>\n\n<div style=\"margin-bottom: 2em\"></div>\n\n<div style=\"display: flex; justify-content: space-around; align-items: center; font-size: 120%;\">\n  <div><a href=\"https://arxiv.org/abs/2402.05930\">📄Paper</a></div>\n  <div><a href=\"https://mcgill-nlp.github.io/weblinx\">🌐Website</a></div>\n  <div><a href=\"https://colab.research.google.com/github/McGill-NLP/weblinx/blob/main/examples/WebLINX_Colab_Notebook.ipynb\">📓Colab</a></div>\n  <div><a href=\"https://huggingface.co/datasets/McGill-NLP/WebLINX\">🤗Dataset</a></div>\n  <div><a href=\"https://github.com/McGill-NLP/weblinx\">💾Code</a></div>\n</div>\n\n\n## Quickstart\n\n```python\nfrom datasets import load_dataset\nfrom huggingface_hub import snapshot_download\nfrom transformers import pipeline\n\n# Load validation split\nvalid = load_dataset(\"McGill-NLP/weblinx\", split=\"validation\")\n\n# Download and load the templates\nsnapshot_download(\n    \"McGill-NLP/WebLINX\", repo_type=\"dataset\", allow_patterns=\"templates/*.txt\", local_dir=\"./\"\n)\nwith open('templates/llama.txt') as f:\n    template = f.read()\n\nturn = valid[0]\nturn_text = template.format(**turn)\n\n# Load action model and input the text to get prediction\naction_model = pipeline(\n    model=\"McGill-NLP/Sheared-LLaMA-2.7B-weblinx\", device=0, torch_dtype='auto'\n)\nout = action_model(turn_text, return_full_text=False, max_new_tokens=64, truncation=True)\npred = out[0]['generated_text']\n\nprint(\"Ref:\", turn[\"action\"])\nprint(\"Pred:\", pred)\n```\n\n\n## Original Model\n\nThis model is finetuned on WebLINX using checkpoints previously published on Huggingface Hub.\\\n[Click here to access the original model.](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B)\n\n\n## License\n\nThis model is derived from LLaMA-2, which can only be used with the [LLaMA 2 Community License Agreement](https://github.com/facebookresearch/llama/blob/main/LICENSE). By using or distributing any portion or element of this model, you agree to be bound by this Agreement.\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2402.05930",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 127,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-22T17:16:23.000Z",
  "created_at": "2024-09-22T16:25:16.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66f044ecdf079df1a3c15cfa",
  "id": "RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf",
  "modelId": "RichardErkhov/McGill-NLP_-_Sheared-LLaMA-2.7B-weblinx-gguf",
  "sha": "15ebdda4fd16152ee357b8c9290c72e3ae06176b",
  "createdAt": "2024-09-22T16:25:16.000Z",
  "lastModified": "2024-09-22T17:16:23.000Z",
  "author": "RichardErkhov",
  "downloads": 127,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}