richarderkhov/abacusai_-_giraffe-v2-70b-32k-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/DJHrZmfoy-0TzNChTrtxP.png",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models Giraffe-v2-70b-32k - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Giraffe-v2-70b-32k.Q2_K.gguf | Q2_K | 23.71GB | | Giraffe-v2-70b-32k.IQ3_XS.gguf | IQ3_XS | 26.37GB | | Giraffe-v2-70b-32k.IQ3_S.gguf | IQ3_S | 27.86GB | | Giraffe-v2-70b-32k.Q3_K_S.gguf | Q3_K_S | 27.86GB | | Giraffe-v2-70b-32k.IQ3_M.gguf | IQ3_M | 28.82GB | | Giraffe-v2-70b-32k.Q3_K.gguf | Q3_K | 30.99GB | | Giraffe-v2-70b-32k.Q3_K_M.gguf | Q3_K_M | 30.99GB | | Giraffe-v2-70b-32k.Q3_K_L.gguf | Q3_K_L | 33.67GB | | Giraffe-v2-70b-32k.IQ4_XS.gguf | IQ4_XS | 34.64GB | | Giraffe-v2-70b-32k.Q4_0.gguf | Q4_0 | 36.2GB | | Giraffe-v2-70b-32k.IQ4_NL.gguf | IQ4_NL | 36.55GB | | Giraffe-v2-70b-32k.Q4_K_S.gguf | Q4_K_S | 36.55GB | | Giraffe-v2-70b-32k.Q4_K.gguf | Q4_K | 38.58GB | | Giraffe-v2-70b-32k.Q4_K_M.gguf | Q4_K_M | 38.58GB | | Giraffe-v2-70b-32k.Q4_1.gguf | Q4_1 | 40.2GB | | Giraffe-v2-70b-32k.Q5_0.gguf | Q5_0 | 44.2GB | | Giraffe-v2-70b-32k.Q5_K_S.gguf | Q5_K_S | 44.2GB | | Giraffe-v2-70b-32k.Q5_K.gguf | Q5_K | 45.41GB | | Giraffe-v2-70b-32k.Q5_K_M.gguf | Q5_K_M | 45.41GB | | Giraffe-v2-70b-32k.Q5_1.gguf | Q5_1 | 48.2GB | | Giraffe-v2-70b-32k.Q6_K.gguf | Q6_K | 52.7GB | | Giraffe-v2-70b-32k.Q8_0.gguf | Q8_0 | 68.26GB | Original model description: --- tags: --- !image/png",
    "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\nGiraffe-v2-70b-32k - GGUF\n- Model creator: https://huggingface.co/abacusai/\n- Original model: https://huggingface.co/abacusai/Giraffe-v2-70b-32k/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Giraffe-v2-70b-32k.Q2_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q2_K.gguf) | Q2_K | 23.71GB |\n| [Giraffe-v2-70b-32k.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.IQ3_XS.gguf) | IQ3_XS | 26.37GB |\n| [Giraffe-v2-70b-32k.IQ3_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.IQ3_S.gguf) | IQ3_S | 27.86GB |\n| [Giraffe-v2-70b-32k.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q3_K_S.gguf) | Q3_K_S | 27.86GB |\n| [Giraffe-v2-70b-32k.IQ3_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.IQ3_M.gguf) | IQ3_M | 28.82GB |\n| [Giraffe-v2-70b-32k.Q3_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q3_K.gguf) | Q3_K | 30.99GB |\n| [Giraffe-v2-70b-32k.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q3_K_M.gguf) | Q3_K_M | 30.99GB |\n| [Giraffe-v2-70b-32k.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q3_K_L.gguf) | Q3_K_L | 33.67GB |\n| [Giraffe-v2-70b-32k.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.IQ4_XS.gguf) | IQ4_XS | 34.64GB |\n| [Giraffe-v2-70b-32k.Q4_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q4_0.gguf) | Q4_0 | 36.2GB |\n| [Giraffe-v2-70b-32k.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.IQ4_NL.gguf) | IQ4_NL | 36.55GB |\n| [Giraffe-v2-70b-32k.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/blob/main/Giraffe-v2-70b-32k.Q4_K_S.gguf) | Q4_K_S | 36.55GB |\n| [Giraffe-v2-70b-32k.Q4_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q4_K | 38.58GB |\n| [Giraffe-v2-70b-32k.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q4_K_M | 38.58GB |\n| [Giraffe-v2-70b-32k.Q4_1.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q4_1 | 40.2GB |\n| [Giraffe-v2-70b-32k.Q5_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q5_0 | 44.2GB |\n| [Giraffe-v2-70b-32k.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q5_K_S | 44.2GB |\n| [Giraffe-v2-70b-32k.Q5_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q5_K | 45.41GB |\n| [Giraffe-v2-70b-32k.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q5_K_M | 45.41GB |\n| [Giraffe-v2-70b-32k.Q5_1.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q5_1 | 48.2GB |\n| [Giraffe-v2-70b-32k.Q6_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q6_K | 52.7GB |\n| [Giraffe-v2-70b-32k.Q8_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf/tree/main/) | Q8_0 | 68.26GB |\n\n\n\n\nOriginal model description:\n---\ntags:\n- llama2\n---\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/DJHrZmfoy-0TzNChTrtxP.png)\n\n## Model Details\n\n### Model Description\n\n\nWe have followed up on our previous training runs related to extending the context length\nof Llama models. The associated github repository \n\nhttps://github.com/abacusai/long-context\n\nhas some basic details on our approach and metrics. We have also published a paper on arXiv\nthat covers our experiments and analysis a lot more comprehensively.\n\nhttp://arxiv.org/abs/2308.10882\n\n- **Developed by:** [Abacus.AI](https://abacus.ai)\n- **Model type:** Transformer based autoregressive causal language model\n- **License:** Llama 2 Community License: https://github.com/facebookresearch/llama/blob/main/LICENSE\n- **Finetuned from model:** Llama V2 70B\n\n### Usage\n\nTo use this model at longer lengths the model needs to be patched to interpolate the longer context\nlengths. It will not work if it is simply loaded with the `AutoModel` framework of `transformers`.\nFor full details and usage see:\n\nhttps://github.com/abacusai/Long-Context\n\nThe evaluation section has detailed code for how to load and patch the model for inference (or further fine-tuning).\nNote in particular the `max_position_embeddings` is not relevant since the patched module dynamically reallocates\nthe position buffers as required.\n\nThe tokenizer corresponding to this model is https://huggingface.co/abacusai/Giraffe-v1-Tokenizer.\n\nUsing the code in the repository you can load this model with the following code:\n```python\nfrom models import load_model, load_tokenizer\ntokenizer = load_tokenizer()\nmodel = load_model('abacusai/Giraffe-v2-70b-32k', scale=8)\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2308.10882",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 87,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-28T08:06:25.000Z",
  "created_at": "2024-05-27T11:31:21.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66546f09b1181f7d10b32ffb",
  "id": "RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf",
  "modelId": "RichardErkhov/abacusai_-_Giraffe-v2-70b-32k-gguf",
  "sha": "2c69617ce9b468a2666853c444fa5f6ef71efcdd",
  "createdAt": "2024-05-27T11:31:21.000Z",
  "lastModified": "2024-05-28T08:06:25.000Z",
  "author": "RichardErkhov",
  "downloads": 87,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 32
}