richarderkhov/mychen76_-_mistral-7b-merged-dare-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "mistral-7b-merged-dare is a merge of the following models:",
    "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\nmistral-7b-merged-dare - GGUF\n- Model creator: https://huggingface.co/mychen76/\n- Original model: https://huggingface.co/mychen76/mistral-7b-merged-dare/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [mistral-7b-merged-dare.Q2_K.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q2_K.gguf) | Q2_K | 2.53GB |\n| [mistral-7b-merged-dare.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [mistral-7b-merged-dare.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [mistral-7b-merged-dare.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [mistral-7b-merged-dare.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [mistral-7b-merged-dare.Q3_K.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q3_K.gguf) | Q3_K | 3.28GB |\n| [mistral-7b-merged-dare.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [mistral-7b-merged-dare.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [mistral-7b-merged-dare.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [mistral-7b-merged-dare.Q4_0.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [mistral-7b-merged-dare.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [mistral-7b-merged-dare.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [mistral-7b-merged-dare.Q4_K.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q4_K.gguf) | Q4_K | 4.07GB |\n| [mistral-7b-merged-dare.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [mistral-7b-merged-dare.Q4_1.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [mistral-7b-merged-dare.Q5_0.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [mistral-7b-merged-dare.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [mistral-7b-merged-dare.Q5_K.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q5_K.gguf) | Q5_K | 4.78GB |\n| [mistral-7b-merged-dare.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [mistral-7b-merged-dare.Q5_1.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [mistral-7b-merged-dare.Q6_K.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q6_K.gguf) | Q6_K | 5.53GB |\n| [mistral-7b-merged-dare.Q8_0.gguf](https://huggingface.co/RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf/blob/main/mistral-7b-merged-dare.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\ntags:\n- merge\n---\n\n# mistral-7b-merged-dare\n\nmistral-7b-merged-dare is a merge of the following models:\n\n\n## 🧩 Configuration\n\n```yaml\nmodels:\n  - model: mistralai/Mistral-7B-v0.1\n  - model: samir-fama/SamirGPT-v1\n    parameters:\n      density: 0.53\n      weight: 0.4\n  - model: abacusai/Slerp-CM-mist-dpo\n    parameters:\n      density: 0.53\n      weight: 0.3\n  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2\n    parameters:\n      density: 0.53\n      weight: 0.3\nmerge_method: dare_ties\nbase_model: mistralai/Mistral-7B-v0.1\nparameters:\n  int8_mask: true\ndtype: bfloat16\n\n```\n\n## 💻 Usage\n```python\n!pip install -qU transformers bitsandbytes accelerate\n\nfrom transformers import AutoTokenizer\nimport transformers\nimport torch\n\nmodel = \"mayacinka/West-Ramen-7Bx4\"\n\ntokenizer = AutoTokenizer.from_pretrained(model)\npipeline = transformers.pipeline(\n    \"text-generation\",\n    model=model,\n    model_kwargs={\"torch_dtype\": torch.float16, \"load_in_4bit\": True},\n)\n\nmessages = [{\"role\": \"user\", \"content\": \"Explain what a Mixture of Experts is in less than 100 words.\"}]\nprompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\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# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-dare)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |73.46|\n|AI2 Reasoning Challenge (25-Shot)|69.71|\n|HellaSwag (10-Shot)              |87.05|\n|MMLU (5-Shot)                    |65.07|\n|TruthfulQA (0-shot)              |63.24|\n|Winogrande (5-shot)              |81.61|\n|GSM8k (5-shot)                   |73.01|\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 192,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-12T09:08:15.000Z",
  "created_at": "2024-09-12T04:07:05.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66e268e9420a3111a89e46d2",
  "id": "RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf",
  "modelId": "RichardErkhov/mychen76_-_mistral-7b-merged-dare-gguf",
  "sha": "ec127383daca0779c54ff7c24cd93133dc6660d5",
  "createdAt": "2024-09-12T04:07:05.000Z",
  "lastModified": "2024-09-12T09:08:15.000Z",
  "author": "RichardErkhov",
  "downloads": 192,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}