README.md

---
license: mit
train: false
inference: false
pipeline_tag: text-generation
model-index:
- name: aanaphi2-v0.1
  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: 63.91
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mobiuslabsgmbh/aanaphi2-v0.1
      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: 77.97
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mobiuslabsgmbh/aanaphi2-v0.1
      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: 57.73
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mobiuslabsgmbh/aanaphi2-v0.1
      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: 51.56
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mobiuslabsgmbh/aanaphi2-v0.1
      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: 73.64
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mobiuslabsgmbh/aanaphi2-v0.1
      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: 54.89
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mobiuslabsgmbh/aanaphi2-v0.1
      name: Open LLM Leaderboard
---
*aanaphi2-v0.1* is a finetuned (SFT + DPO) chat model based on <a href="https://huggingface.co/microsoft/phi-2">Microsoft's Phi-2 base model</a> (2.8B parameters). 

![image/gif](https://cdn-uploads.huggingface.co/production/uploads/636b945ef575d3705149e982/pIeboaaroFY5fpomUADrS.gif)

## Performance
| Models            | phi-2            | aanaphi2-v0.1    |
|-------------------|------------------|------------------|
| ARC (25-shot)     | 61.09            | <b>63.74</b>     |
| HellaSwag (10-shot)| 75.11           | <b>78.30</b>     |
| MMLU (5-shot)     | <b>58.11</b>     | 57.70            |
| TruthfulQA-MC2    | 44.47            | <b>51.56</b>     |
| Winogrande (5-shot)| <b>74.35</b>    | 73.40            |
| GSM8K (5-shot)    | 54.81            | <b>58.61</b>     |
| Average           | 61.33            | <b>63.89</b>     |


## Installation
Make sure you have the latest version of the transformers library:
```
pip install pip --upgrade && pip install transformers --upgrade
```

## Basic Usage
``` Python
#Load model
import transformers, torch
compute_dtype = torch.float16
cache_path    = ''
device        = 'cuda'
model_id      = "mobiuslabsgmbh/aanaphi2-v0.1"
model         = transformers.AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype, 
                                                                  cache_dir=cache_path,
                                                                  device_map=device)
tokenizer     = transformers.AutoTokenizer.from_pretrained(model_id, cache_dir=cache_path)

#Set Prompt format
instruction_template = "### Human: "
response_template    = "### Assistant: "
def prompt_format(prompt):
    out = instruction_template + prompt + '\n' + response_template
    return out
model.eval();

@torch.no_grad()
def generate(prompt, max_length=1024):
    prompt_chat = prompt_format(prompt)
    inputs      = tokenizer(prompt_chat, return_tensors="pt", return_attention_mask=True).to('cuda')
    outputs     = model.generate(**inputs, max_length=max_length, eos_token_id= tokenizer.eos_token_id) 
    text        = tokenizer.batch_decode(outputs[:,:-1])[0]
    return text

#Generate
print(generate('If A+B=C and B=C, what would be the value of A?'))
```
# [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_mobiuslabsgmbh__aanaphi2-v0.1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |63.28|
|AI2 Reasoning Challenge (25-Shot)|63.91|
|HellaSwag (10-Shot)              |77.97|
|MMLU (5-Shot)                    |57.73|
|TruthfulQA (0-shot)              |51.56|
|Winogrande (5-shot)              |73.64|
|GSM8k (5-shot)                   |54.89|