richarderkhov/1024m_-_olmoe-1b-7b-0924-base-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "olmoe-logo.png",
    "summary": "> OLMoE-1B-7B is a Mixture-of-Experts LLM with 1B active and 7B total parameters released in September 2024 (0924). It yields state-of-the-art performance among models with a similar cost (1B) and is competitive with much larger models like Llama2-13B. OLMoE is 100% open-source. This information and more can also be found on the **OLMoE GitHub repository**. # Use Install transformers **from source** until a release after this PR & torch and run: ``python from transformers import OlmoeForCausalLM, AutoTokenizer import torch DEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\" # Load different ckpts via passing e.g. revision=step10000-tokens41B model = OlmoeForCausalLM.from_pretrained(\"allenai/OLMoE-1B-7B-0924\").to(DEVICE) tokenizer = AutoTokenizer.from_pretrained(\"allenai/OLMoE-1B-7B-0924\") inputs = tokenizer(\"Bitcoin is\", return_tensors=\"pt\") inputs = {k: v.to(DEVICE) for k, v in inputs.items()} out = model.generate(**inputs, max_length=64) print(tokenizer.decode(out[0])) # > # Bitcoin is a digital currency that is created and held electronically. No one controls it. Bitcoins aren’t printed, like dollars or euros – they’re produced by people and businesses running computers all around the world, using software that solves mathematical ` You can list all revisions/branches by installing huggingface-hub & running: `python from huggingface_hub import list_repo_refs out = list_repo_refs(\"OLMoE/OLMoE-1B-7B-0924\") branches = [b.name for b in out.branches] ` Important branches: # Evaluation Snapshot | Model                       | Active Params | Open Data | MMLU | HellaSwag | ARC-Chall. | ARC-Easy | PIQA | WinoGrande | |-----------------------------|---------------|-----------|------|-----------|------------|----------|------|------------| | **LMs with ~1B active parameters** |               |           |      |           |            |          |      |            | | **OLMoE-1B-7B**              | **1.3B**      | **✅**    | **54.1** | **80.0** | **62.1**   | **84.2** | **79.8** | **70.2**  | | DCLM-1B                     | 1.4B          | ✅        | 48.5 | 75.1      | 57.6       | 79.5     | 76.6 | 68.1       | | TinyLlama-1B                | 1.1B          | ✅        | 33.6 | 60.8      | 38.1       | 69.5     | 71.7 | 60.1       | | OLMo-1B (0724)              | 1.3B          | ✅        | 32.1 | 67.5      | 36.4       | 53.5     | 74.0 | 62.9       | | Pythia-1B                   | 1.1B          | ✅        | 31.1 | 48.0      | 31.4       | 63.4     | 68.9 | 52.7       | | **LMs with ~2-3B active parameters** |               |           |      |           |            |          |      |            | | Qwen1.5-3B-14B              | 2.7B          | ❌        | **62.4** | 80.0      | **77.4**   | **91.6** | **81.0** | 72.3 | | Gemma2-3B                   | 2.6B          | ❌        | 53.3 | 74.6      | 67.5       | 84.3     | 78.5 | 71.8       | | JetMoE-2B-9B                | 2.2B          | ❌        | 49.1 | **81.7**  | 61.4       | 81.9     | 80.3 | 70.7       | | DeepSeek-3B-16B             | 2.9B          | ❌        | 45.5 | 80.4      | 53.4       | 82.7     | 80.1 | **73.2**   | | StableLM-2B                 | 1.6B          | ❌        | 40.4 | 70.3      | 50.6       | 75.3     | 75.6 | 65.8       | | OpenMoE-3B-9B               | 2.9B          | ✅        | 27.4 | 44.4      | 29.3       | 50.6     | 63.3 | 51.9       | | **LMs with ~7-9B active parameters** |               |           |      |           |            |          |      |            | | Gemma2-9B                   | 9.2B          | ❌        | **70.6** | **87.3**  | **89.5**   | **95.5** | **86.1** | **78.8** | | Llama3.1-8B                 | 8.0B          | ❌        | 66.9 | 81.6      | 79.5       | 91.7     | 81.1 | 76.6       | | DCLM-7B                     | 6.9B          | ✅        | 64.4 | 82.3      | 79.8       | 92.3     | 80.1 | 77.3       | | Mistral-7B                  | 7.3B          | ❌        | 64.0 | 83.0      | 78.6       | 90.8     | 82.8 | 77.9       | | OLMo-7B (0724)              | 6.9B          | ✅        | 54.9 | 80.5      | 68.0       | 85.7     | 79.3 | 73.2       | | Llama2-7B                   | 6.7B          | ❌        | 46.2 | 78.9      | 54.2       | 84.0     | 77.5 | 71.7       | # Citation `bibtex @misc{muennighoff2024olmoeopenmixtureofexpertslanguage, title={OLMoE: Open Mixture-of-Experts Language Models}, author={Niklas Muennighoff and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Jacob Morrison and Sewon Min and Weijia Shi and Pete Walsh and Oyvind Tafjord and Nathan Lambert and Yuling Gu and Shane Arora and Akshita Bhagia and Dustin Schwenk and David Wadden and Alexander Wettig and Binyuan Hui and Tim Dettmers and Douwe Kiela and Ali Farhadi and Noah A. Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi}, year={2024}, eprint={2409.02060}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2409.02060}, } ``",
    "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\nOLMoE-1B-7B-0924-Base - GGUF\n- Model creator: https://huggingface.co/1024m/\n- Original model: https://huggingface.co/1024m/OLMoE-1B-7B-0924-Base/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [OLMoE-1B-7B-0924-Base.Q2_K.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q2_K.gguf) | Q2_K | 2.39GB |\n| [OLMoE-1B-7B-0924-Base.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q3_K_S.gguf) | Q3_K_S | 2.82GB |\n| [OLMoE-1B-7B-0924-Base.Q3_K.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q3_K.gguf) | Q3_K | 3.11GB |\n| [OLMoE-1B-7B-0924-Base.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q3_K_M.gguf) | Q3_K_M | 3.11GB |\n| [OLMoE-1B-7B-0924-Base.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q3_K_L.gguf) | Q3_K_L | 3.36GB |\n| [OLMoE-1B-7B-0924-Base.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.IQ4_XS.gguf) | IQ4_XS | 3.5GB |\n| [OLMoE-1B-7B-0924-Base.Q4_0.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q4_0.gguf) | Q4_0 | 3.66GB |\n| [OLMoE-1B-7B-0924-Base.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.IQ4_NL.gguf) | IQ4_NL | 3.69GB |\n| [OLMoE-1B-7B-0924-Base.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q4_K_S.gguf) | Q4_K_S | 3.69GB |\n| [OLMoE-1B-7B-0924-Base.Q4_K.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q4_K.gguf) | Q4_K | 3.92GB |\n| [OLMoE-1B-7B-0924-Base.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q4_K_M.gguf) | Q4_K_M | 3.92GB |\n| [OLMoE-1B-7B-0924-Base.Q4_1.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q4_1.gguf) | Q4_1 | 4.05GB |\n| [OLMoE-1B-7B-0924-Base.Q5_0.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q5_0.gguf) | Q5_0 | 4.45GB |\n| [OLMoE-1B-7B-0924-Base.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q5_K_S.gguf) | Q5_K_S | 4.45GB |\n| [OLMoE-1B-7B-0924-Base.Q5_K.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q5_K.gguf) | Q5_K | 4.59GB |\n| [OLMoE-1B-7B-0924-Base.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q5_K_M.gguf) | Q5_K_M | 4.59GB |\n| [OLMoE-1B-7B-0924-Base.Q5_1.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q5_1.gguf) | Q5_1 | 4.85GB |\n| [OLMoE-1B-7B-0924-Base.Q6_K.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q6_K.gguf) | Q6_K | 5.29GB |\n| [OLMoE-1B-7B-0924-Base.Q8_0.gguf](https://huggingface.co/RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf/blob/main/OLMoE-1B-7B-0924-Base.Q8_0.gguf) | Q8_0 | 6.85GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nlanguage:\n- en\ntags:\n- moe\n- olmo\n- olmoe\nco2_eq_emissions: 1\ndatasets:\n- allenai/OLMoE-mix-0924\nlibrary_name: transformers\n---\n\n<img alt=\"OLMoE Logo.\" src=\"olmoe-logo.png\" width=\"250px\">\n\n\n# Model Summary\n\n> OLMoE-1B-7B is a Mixture-of-Experts LLM with 1B active and 7B total parameters released in September 2024 (0924). It yields state-of-the-art performance among models with a similar cost (1B) and is competitive with much larger models like Llama2-13B. OLMoE is 100% open-source.\n\nThis information and more can also be found on the [**OLMoE GitHub repository**](https://github.com/allenai/OLMoE).\n- **Paper**: https://arxiv.org/abs/2409.02060\n- **Pretraining** [Checkpoints](https://hf.co/allenai/OLMoE-1B-7B-0924), [Code](https://github.com/allenai/OLMo/tree/Muennighoff/MoE), [Data](https://huggingface.co/datasets/allenai/OLMoE-mix-0924) and [Logs](https://wandb.ai/ai2-llm/olmoe/reports/OLMoE-1B-7B-0924--Vmlldzo4OTcyMjU3).\n- **SFT (Supervised Fine-Tuning)** [Checkpoints](https://huggingface.co/allenai/OLMoE-1B-7B-0924-SFT), [Code](https://github.com/allenai/open-instruct/tree/olmoe-sft), [Data](https://hf.co/datasets/allenai/tulu-v3.1-mix-preview-4096-OLMoE) and [Logs](https://github.com/allenai/OLMoE/blob/main/logs/olmoe-sft-logs.txt).\n- **DPO/KTO (Direct Preference Optimization/Kahneman-Tversky Optimization)**, [Checkpoints](https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct), [Preference Data](https://hf.co/datasets/allenai/ultrafeedback_binarized_cleaned), [DPO code](https://github.com/allenai/open-instruct/tree/olmoe-sft), [KTO code](https://github.com/Muennighoff/kto/blob/master/kto.py) and [Logs](https://github.com/allenai/OLMoE/blob/main/logs/olmoe-dpo-logs.txt).\n\n# Use\n\nInstall `transformers` **from source** until a release after [this PR](https://github.com/huggingface/transformers/pull/32406) & `torch` and run:\n\n```python\nfrom transformers import OlmoeForCausalLM, AutoTokenizer\nimport torch\n\nDEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n\n# Load different ckpts via passing e.g. `revision=step10000-tokens41B`\nmodel = OlmoeForCausalLM.from_pretrained(\"allenai/OLMoE-1B-7B-0924\").to(DEVICE)\ntokenizer = AutoTokenizer.from_pretrained(\"allenai/OLMoE-1B-7B-0924\")\ninputs = tokenizer(\"Bitcoin is\", return_tensors=\"pt\")\ninputs = {k: v.to(DEVICE) for k, v in inputs.items()}\nout = model.generate(**inputs, max_length=64)\nprint(tokenizer.decode(out[0]))\n# > # Bitcoin is a digital currency that is created and held electronically. No one controls it. Bitcoins aren’t printed, like dollars or euros – they’re produced by people and businesses running computers all around the world, using software that solves mathematical\n```\n\nYou can list all revisions/branches by installing `huggingface-hub` & running:\n```python\nfrom huggingface_hub import list_repo_refs\nout = list_repo_refs(\"OLMoE/OLMoE-1B-7B-0924\")\nbranches = [b.name for b in out.branches]\n```\n\nImportant branches:\n- `step1200000-tokens5033B`: Pretraining checkpoint used for annealing. There are a few more checkpoints after this one but we did not use them.\n- `main`: Checkpoint annealed from `step1200000-tokens5033B` for an additional 100B tokens (23,842 steps). We use this checkpoint for our adaptation (https://huggingface.co/allenai/OLMoE-1B-7B-0924-SFT & https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct).\n- `fp32`: FP32 version of `main`. The model weights were stored in FP32 during training but we did not observe any performance drop from casting them to BF16 after training so we upload all weights in BF16. If you want the original FP32 checkpoint for `main` you can use this one. You will find that it yields slightly different results but should perform around the same on benchmarks.\n\n# Evaluation Snapshot\n\n| Model                       | Active Params | Open Data | MMLU | HellaSwag | ARC-Chall. | ARC-Easy | PIQA | WinoGrande |\n|-----------------------------|---------------|-----------|------|-----------|------------|----------|------|------------|\n| **LMs with ~1B active parameters** |               |           |      |           |            |          |      |            |\n| **OLMoE-1B-7B**              | **1.3B**      | **✅**    | **54.1** | **80.0** | **62.1**   | **84.2** | **79.8** | **70.2**  |\n| DCLM-1B                     | 1.4B          | ✅        | 48.5 | 75.1      | 57.6       | 79.5     | 76.6 | 68.1       |\n| TinyLlama-1B                | 1.1B          | ✅        | 33.6 | 60.8      | 38.1       | 69.5     | 71.7 | 60.1       |\n| OLMo-1B (0724)              | 1.3B          | ✅        | 32.1 | 67.5      | 36.4       | 53.5     | 74.0 | 62.9       |\n| Pythia-1B                   | 1.1B          | ✅        | 31.1 | 48.0      | 31.4       | 63.4     | 68.9 | 52.7       |\n| **LMs with ~2-3B active parameters** |               |           |      |           |            |          |      |            |\n| Qwen1.5-3B-14B              | 2.7B          | ❌        | **62.4** | 80.0      | **77.4**   | **91.6** | **81.0** | 72.3 |\n| Gemma2-3B                   | 2.6B          | ❌        | 53.3 | 74.6      | 67.5       | 84.3     | 78.5 | 71.8       |\n| JetMoE-2B-9B                | 2.2B          | ❌        | 49.1 | **81.7**  | 61.4       | 81.9     | 80.3 | 70.7       |\n| DeepSeek-3B-16B             | 2.9B          | ❌        | 45.5 | 80.4      | 53.4       | 82.7     | 80.1 | **73.2**   |\n| StableLM-2B                 | 1.6B          | ❌        | 40.4 | 70.3      | 50.6       | 75.3     | 75.6 | 65.8       |\n| OpenMoE-3B-9B               | 2.9B          | ✅        | 27.4 | 44.4      | 29.3       | 50.6     | 63.3 | 51.9       |\n| **LMs with ~7-9B active parameters** |               |           |      |           |            |          |      |            |\n| Gemma2-9B                   | 9.2B          | ❌        | **70.6** | **87.3**  | **89.5**   | **95.5** | **86.1** | **78.8** |\n| Llama3.1-8B                 | 8.0B          | ❌        | 66.9 | 81.6      | 79.5       | 91.7     | 81.1 | 76.6       |\n| DCLM-7B                     | 6.9B          | ✅        | 64.4 | 82.3      | 79.8       | 92.3     | 80.1 | 77.3       |\n| Mistral-7B                  | 7.3B          | ❌        | 64.0 | 83.0      | 78.6       | 90.8     | 82.8 | 77.9       |\n| OLMo-7B (0724)              | 6.9B          | ✅        | 54.9 | 80.5      | 68.0       | 85.7     | 79.3 | 73.2       |\n| Llama2-7B                   | 6.7B          | ❌        | 46.2 | 78.9      | 54.2       | 84.0     | 77.5 | 71.7       |\n\n# Citation\n\n```bibtex\n@misc{muennighoff2024olmoeopenmixtureofexpertslanguage,\n      title={OLMoE: Open Mixture-of-Experts Language Models}, \n      author={Niklas Muennighoff and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Jacob Morrison and Sewon Min and Weijia Shi and Pete Walsh and Oyvind Tafjord and Nathan Lambert and Yuling Gu and Shane Arora and Akshita Bhagia and Dustin Schwenk and David Wadden and Alexander Wettig and Binyuan Hui and Tim Dettmers and Douwe Kiela and Ali Farhadi and Noah A. Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi},\n      year={2024},\n      eprint={2409.02060},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2409.02060}, \n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2409.02060",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 818,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-26T07:45:24.000Z",
  "created_at": "2024-10-26T04:55:41.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "671c764d07338f680d87c6d9",
  "id": "RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf",
  "modelId": "RichardErkhov/1024m_-_OLMoE-1B-7B-0924-Base-gguf",
  "sha": "3846a2c1b71afa869956316772a25058889aeb99",
  "createdAt": "2024-10-26T04:55:41.000Z",
  "lastModified": "2024-10-26T07:45:24.000Z",
  "author": "RichardErkhov",
  "downloads": 818,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}