README.md

---
license: apache-2.0
model-index:
- name: orca_mini_v7_72b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 59.3
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v7_72b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 55.06
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v7_72b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 26.44
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v7_72b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 18.01
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v7_72b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 24.21
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v7_72b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 51.35
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=pankajmathur/orca_mini_v7_72b
      name: Open LLM Leaderboard
---

**Model Name: Qwen2 orca_mini_v7_72b**
# Qwen2 orca_mini_v7_72b is trained with various SFT Datasets

<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />

<strong>
"Obsessed with GenAI's potential? So am I ! Let's create together 🚀 <a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a>"
</strong>

<br>

### NOTICE
By providing proper credit and attribution, you are granted permission to use this model as a foundational base for further Full fine tuning, DPO, PPO or ORPO tuning and any kind of Merges. 
I actively encourage users to customize and enhance the model according to their specific needs, as this version is designed to be a comprehensive general model. 
Dive in and innovate!


### Example Usage
Here is the ChatML prompt format
```
<|im_start|>system
You are Orca Mini, a helpful AI assistant.<|im_end|>
<|im_start|>user
Hello Orca Mini, what can you do for me?<|im_end|>
<|im_start|>assistant
```
Below shows a code example on how to use this model

```python
from transformers import AutoModel, AutoTokenizer
model_slug = "pankajmathur/orca_mini_v7_72b"
model = AutoModel.from_pretrained(model_slug)
tokenizer = AutoTokenizer.from_pretrained(model_slug)
messages = [
    {"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
    {"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```

**Quants**

GGUF : Coming Soon

AWQ: Coming Soon


### Processing Long Texts (Based upon Qwen2-7B-Instruct suggestions at https://huggingface.co/Qwen/Qwen2-7B-Instruct)

To handle extensive inputs exceeding 32,768 tokens, we utilize [YARN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.

For deployment, we recommend using vLLM. You can enable the long-context capabilities by following these steps:

1. **Install vLLM**: You can install vLLM by running the following command.

```bash
pip install "vllm>=0.4.3"
```

Or you can install vLLM from [source](https://github.com/vllm-project/vllm/).

2. **Configure Model Settings**: After downloading the model weights, modify the `config.json` file by including the below snippet:
    ```json
        {
            "architectures": [
                "Qwen2ForCausalLM"
            ],
            // ...
            "vocab_size": 152064,
            // adding the following snippets
            "rope_scaling": {
                "factor": 4.0,
                "original_max_position_embeddings": 32768,
                "type": "yarn"
            }
        }
    ```
    This snippet enable YARN to support longer contexts.

3. **Model Deployment**: Utilize vLLM to deploy your model. For instance, you can set up an openAI-like server using the command:

    ```bash
    python -u -m vllm.entrypoints.openai.api_server --model pankajmathur/orca_mini_v7_72b
    ```
    Then you can access the Chat API by:
    ```bash
    curl http://localhost:8000/v1/chat/completions \
        -H "Content-Type: application/json" \
        -d '{
        "model": "pankajmathur/orca_mini_v7_72b",
        "messages": [
          {"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
          {"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
        ]
        }'
    ```
**Note**: Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required.

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_pankajmathur__orca_mini_v7_72b)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |39.06|
|IFEval (0-Shot)    |59.30|
|BBH (3-Shot)       |55.06|
|MATH Lvl 5 (4-Shot)|26.44|
|GPQA (0-shot)      |18.01|
|MuSR (0-shot)      |24.21|
|MMLU-PRO (5-shot)  |51.35|


[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)