richarderkhov/adamo1139_-_aya-expanse-32b-ungated-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "aya-expanse-32B.png",
    "summary": "Aya-Expanse 32B, but not gated!  **Aya Expanse 32B** is an open-weight research release of a model with highly advanced multilingual capabilities. It focuses on pairing a highly performant pre-trained Command family of models with the result of a year’s dedicated research from Cohere For AI, including data arbitrage, multilingual preference training, safety tuning, and model merging. The result is a powerful multilingual large language model serving 23 languages. This model card corresponds to the 32-billion version of the Aya Expanse model. We also released an 8-billion version which you can find here. ### Supported Languages We cover 23 languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese. ### Try it: Aya Expanse in Action Use the Cohere playground or our Hugging Face Space for interactive exploration. ### How to Use Aya Expanse Install the transformers library and load Aya Expanse 32B as follows: ```python from transformers import AutoTokenizer, AutoModelForCausalLM model_id = \"CohereForAI/aya-expanse-32b\" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) # Format message with the chat template messages = [{\"role\": \"user\", \"content\": \"Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz\"}] input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\")",
    "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\naya-expanse-32b-ungated - GGUF\n- Model creator: https://huggingface.co/adamo1139/\n- Original model: https://huggingface.co/adamo1139/aya-expanse-32b-ungated/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [aya-expanse-32b-ungated.Q2_K.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q2_K.gguf) | Q2_K | 11.93GB |\n| [aya-expanse-32b-ungated.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q3_K_S.gguf) | Q3_K_S | 13.7GB |\n| [aya-expanse-32b-ungated.Q3_K.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q3_K.gguf) | Q3_K | 15.12GB |\n| [aya-expanse-32b-ungated.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q3_K_M.gguf) | Q3_K_M | 15.12GB |\n| [aya-expanse-32b-ungated.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q3_K_L.gguf) | Q3_K_L | 16.36GB |\n| [aya-expanse-32b-ungated.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.IQ4_XS.gguf) | IQ4_XS | 16.75GB |\n| [aya-expanse-32b-ungated.Q4_0.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q4_0.gguf) | Q4_0 | 17.43GB |\n| [aya-expanse-32b-ungated.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.IQ4_NL.gguf) | IQ4_NL | 17.59GB |\n| [aya-expanse-32b-ungated.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q4_K_S.gguf) | Q4_K_S | 17.55GB |\n| [aya-expanse-32b-ungated.Q4_K.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q4_K.gguf) | Q4_K | 18.44GB |\n| [aya-expanse-32b-ungated.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q4_K_M.gguf) | Q4_K_M | 18.44GB |\n| [aya-expanse-32b-ungated.Q4_1.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q4_1.gguf) | Q4_1 | 19.19GB |\n| [aya-expanse-32b-ungated.Q5_0.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q5_0.gguf) | Q5_0 | 20.95GB |\n| [aya-expanse-32b-ungated.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q5_K_S.gguf) | Q5_K_S | 20.95GB |\n| [aya-expanse-32b-ungated.Q5_K.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q5_K.gguf) | Q5_K | 21.47GB |\n| [aya-expanse-32b-ungated.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q5_K_M.gguf) | Q5_K_M | 21.47GB |\n| [aya-expanse-32b-ungated.Q5_1.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q5_1.gguf) | Q5_1 | 22.71GB |\n| [aya-expanse-32b-ungated.Q6_K.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q6_K.gguf) | Q6_K | 24.68GB |\n| [aya-expanse-32b-ungated.Q8_0.gguf](https://huggingface.co/RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf/blob/main/aya-expanse-32b-ungated.Q8_0.gguf) | Q8_0 | 31.97GB |\n\n\n\n\nOriginal model description:\n---\ninference: false\nlibrary_name: transformers\nlanguage:\n- en\n- fr\n- de\n- es\n- it\n- pt\n- ja\n- ko\n- zh\n- ar\n- el\n- fa\n- pl\n- id\n- cs\n- he\n- hi\n- nl\n- ro\n- ru\n- tr\n- uk\n- vi\nlicense: cc-by-nc-4.0\n---\n\n# Model Card for Aya-Expanse-32B Ungated\n\nAya-Expanse 32B, but not gated!\n\n<img src=\"aya-expanse-32B.png\" width=\"650\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>\n\n**Aya Expanse 32B** is an open-weight research release of a model with highly advanced multilingual capabilities. It focuses on pairing a highly performant pre-trained [Command family](https://huggingface.co/CohereForAI/c4ai-command-r-plus) of models with the result of a year’s dedicated research from [Cohere For AI](https://cohere.for.ai/), including [data arbitrage](https://arxiv.org/pdf/2408.14960), [multilingual preference training](https://arxiv.org/abs/2407.02552), [safety tuning](https://arxiv.org/abs/2406.18682), and [model merging](https://arxiv.org/abs/2410.10801). The result is a powerful multilingual large language model serving 23 languages.\n\nThis model card corresponds to the 32-billion version of the Aya Expanse model. We also released an 8-billion version which you can find [here](https://huggingface.co/CohereForAI/aya-expanse-8B).\n\n- Developed by: [Cohere For AI](https://cohere.for.ai/) \n- Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/)\n- License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)\n- Model: Aya Expanse 32B\n- Model Size: 32 billion parameters\n\n### Supported Languages\n\nWe cover 23 languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese.\n\n### Try it: Aya Expanse in Action\n\nUse the [Cohere playground](https://dashboard.cohere.com/playground/chat) or our [Hugging Face Space](https://huggingface.co/spaces/CohereForAI/aya_expanse) for interactive exploration.\n\n\n### How to Use Aya Expanse\n\nInstall the transformers library and load Aya Expanse 32B as follows:\n\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\nmodel_id = \"CohereForAI/aya-expanse-32b\"\ntokenizer = AutoTokenizer.from_pretrained(model_id)\nmodel = AutoModelForCausalLM.from_pretrained(model_id)\n\n# Format message with the chat template\nmessages = [{\"role\": \"user\", \"content\": \"Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz\"}]\ninput_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\")\n## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n\ngen_tokens = model.generate(\n    input_ids, \n    max_new_tokens=100, \n    do_sample=True, \n    temperature=0.3,\n    )\n\ngen_text = tokenizer.decode(gen_tokens[0])\nprint(gen_text)\n```\n\n### Example Notebooks\n\n**Fine-Tuning:**\n- [Detailed Fine-Tuning Notebook](https://colab.research.google.com/drive/1ryPYXzqb7oIn2fchMLdCNSIH5KfyEtv4).\n\n**Community-Contributed Use Cases:**:\n\nThe following notebooks contributed by *Cohere For AI Community* members show how Aya Expanse can be used for different use cases:\n- [Mulitlingual Writing Assistant](https://colab.research.google.com/drive/1SRLWQ0HdYN_NbRMVVUHTDXb-LSMZWF60)\n- [AyaMCooking](https://colab.research.google.com/drive/1-cnn4LXYoZ4ARBpnsjQM3sU7egOL_fLB?usp=sharing)\n- [Multilingual Question-Answering System](https://colab.research.google.com/drive/1bbB8hzyzCJbfMVjsZPeh4yNEALJFGNQy?usp=sharing)\n\n\n## Model Details\n\n**Input**: Models input text only.\n\n**Output**: Models generate text only.\n\n**Model Architecture**: Aya Expanse 32B is an auto-regressive language model that uses an optimized transformer architecture. Post-training includes supervised finetuning, preference training, and model merging.\n\n**Languages covered**: The model is particularly optimized for multilinguality and supports the following languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese\n\n**Context length**: 128K\n\n### Evaluation\n\nWe evaluated Aya Expanse 8B against Gemma 2 9B, Llama 3.1 8B, Ministral 8B, and Qwen 2.5 7B using m-ArenaHard, a dataset based on the [Arena-Hard-Auto dataset](https://huggingface.co/datasets/lmarena-ai/arena-hard-auto-v0.1) and translated to the 23 languages we support in Aya Expanse 8B. Win-rates were determined using gpt-4o-2024-08-06 as a judge. For a conservative benchmark, we report results from gpt-4o-2024-08-06, though gpt-4o-mini scores showed even stronger performance.\n\nThe m-ArenaHard dataset, used to evaluate Aya Expanse’s capabilities, is publicly available [here](https://huggingface.co/datasets/CohereForAI/m-ArenaHard).\n\n\n<img src=\"winrates_marenahard_complete.png\" width=\"650\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>\n\n\n### Model Card Contact\n\nFor errors or additional questions about details in this model card, contact info@for.ai.\n\n### Terms of Use\n\nWe hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant multilingual model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy).\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2408.14960",
    "arxiv:2407.02552",
    "arxiv:2406.18682",
    "arxiv:2410.10801",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 1661,
  "gated": false,
  "private": false,
  "last_modified": "2024-11-13T06:28:39.000Z",
  "created_at": "2024-11-12T14:45:51.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67336a1f5b8d4dccb4e1f72f",
  "id": "RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf",
  "modelId": "RichardErkhov/adamo1139_-_aya-expanse-32b-ungated-gguf",
  "sha": "7c2971787ac7e310593c183139350de681f94227",
  "createdAt": "2024-11-12T14:45:51.000Z",
  "lastModified": "2024-11-13T06:28:39.000Z",
  "author": "RichardErkhov",
  "downloads": 1661,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}