README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Locutusque/Hercules-2.5-Mistral-7B
- teknium/OpenHermes-2.5-Mistral-7B
base_model:
- Locutusque/Hercules-2.5-Mistral-7B
- teknium/OpenHermes-2.5-Mistral-7B
model-index:
- name: OpenHercules-2.5-Mistral-7B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 64.25
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenHercules-2.5-Mistral-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 84.84
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenHercules-2.5-Mistral-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 64.21
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenHercules-2.5-Mistral-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 47.84
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenHercules-2.5-Mistral-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 78.93
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenHercules-2.5-Mistral-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 59.21
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenHercules-2.5-Mistral-7B
      name: Open LLM Leaderboard
---

# OpenHercules-2.5-Mistral-7B

![image](https://cdn-lfs-us-1.huggingface.co/repos/e1/57/e157f742626af16e1d00d4f7553e4527a069f266f5d8af3792d88fd5e891da37/fc34f01ba8e87f43a2d76beec0b00e0c85e6eeb90ceeed9b90af04814b5c6508?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27OpenHercules.png%3B+filename%3D%22OpenHercules.png%22%3B&response-content-type=image%2Fpng&Expires=1709785276&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcwOTc4NTI3Nn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2UxLzU3L2UxNTdmNzQyNjI2YWYxNmUxZDAwZDRmNzU1M2U0NTI3YTA2OWYyNjZmNWQ4YWYzNzkyZDg4ZmQ1ZTg5MWRhMzcvZmMzNGYwMWJhOGU4N2Y0M2EyZDc2YmVlYzBiMDBlMGM4NWU2ZWViOTBjZWVlZDliOTBhZjA0ODE0YjVjNjUwOD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=Im-0nS-MKPMlDh1n%7EEC65TPfOlky9y3i7POGl7U0j5BxtbzJL9K-I0NojJSP2qlpXGMxIwqJFOj7BVnuNbRjZFsLxnmJIkhGbw2Dhfs6QFmE387KuFRiby3ReO81Zns5i3FOld2D8DJJGgWEpqQfP3neXC7uH8e2MClOha8hJ5IsFM2Om4QkRgW9U25vcX%7EAC1ZDdBDf3cSfYQEQOAtJgT-UXVzGN2X1T9uQaDQS4fWHBVeiQWMHJyGQ5m5iJYiDdqA9B3PnZGCxKJypieFIiJfBdnMtJbpHVNdEJfitIt5sw-dbkgtCego3r7mvvo7shQDY5sU6jYG5q9NblKiOng__&Key-Pair-Id=KCD77M1F0VK2B)

OpenHercules-2.5-Mistral-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Locutusque/Hercules-2.5-Mistral-7B](https://huggingface.co/Locutusque/Hercules-2.5-Mistral-7B)
* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: Locutusque/Hercules-2.5-Mistral-7B
        layer_range: [0, 32]
      - model: teknium/OpenHermes-2.5-Mistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Locutusque/Hercules-2.5-Mistral-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Locutusque/OpenHercules-2.5-Mistral-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Locutusque__OpenHercules-2.5-Mistral-7B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |66.55|
|AI2 Reasoning Challenge (25-Shot)|64.25|
|HellaSwag (10-Shot)              |84.84|
|MMLU (5-Shot)                    |64.21|
|TruthfulQA (0-shot)              |47.84|
|Winogrande (5-shot)              |78.93|
|GSM8k (5-shot)                   |59.21|

## Quants

exl2 and gguf by Bartowski: https://huggingface.co/bartowski/OpenHercules-2.5-Mistral-7B-exl2 https://huggingface.co/bartowski/OpenHercules-2.5-Mistral-7B-GGUF
awq by solidrust: https://huggingface.co/solidrust/OpenHercules-2.5-Mistral-7B-AWQ