README.md

---
license: apache-2.0
library_name: transformers
model-index:
- name: laser-dolphin-mixtral-4x7b-dpo
  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: 64.93
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/laser-dolphin-mixtral-4x7b-dpo
      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: 85.81
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/laser-dolphin-mixtral-4x7b-dpo
      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: 63.04
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/laser-dolphin-mixtral-4x7b-dpo
      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: 63.77
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/laser-dolphin-mixtral-4x7b-dpo
      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: 77.82
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/laser-dolphin-mixtral-4x7b-dpo
      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: 44.88
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/laser-dolphin-mixtral-4x7b-dpo
      name: Open LLM Leaderboard
---
# Laser-Dolphin-Mixtral-4x7b-dpo

![laser_dolphin_image](./dolphin_moe.png)

Credit to Fernando Fernandes and Eric Hartford for their project [laserRMT](https://github.com/cognitivecomputations/laserRMT)

This model is a medium-sized MoE implementation based on [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)

The process is outlined in this [notebook](https://github.com/cognitivecomputations/laserRMT/blob/main/examples/laser-dolphin-mixtral-2x7b.ipynb)

## Code Example

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

def generate_response(prompt):
    """
    Generate a response from the model based on the input prompt.

    Args:
    prompt (str): Prompt for the model.

    Returns:
    str: The generated response from the model.
    """
    # Tokenize the input prompt
    inputs = tokenizer(prompt, return_tensors="pt")

    # Generate output tokens
    outputs = model.generate(**inputs, max_new_tokens=256, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id)

    # Decode the generated tokens to a string
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    return response

# Load the model and tokenizer
model_id = "macadeliccc/laser-dolphin-mixtral-4x7b-dpo"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)

prompt = "Write a quicksort algorithm in python"

# Generate and print responses for each language
print("Response:")
print(generate_response(prompt), "\n")
```

## Example output

can you write me a quicksort algorithm in python?

Sure, here's a quicksort algorithm implemented in Python:

```python
def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)
```

This implementation uses the median of the array as the pivot. 
It first checks if the array has one or fewer elements, in which case it is already sorted and can be returned as is.
Otherwise, it selects the pivot as the middle element of the array. Then, it partitions the array into three sub-arrays: elements less than the pivot, elements equal to the pivot, and elements greater than the pivot. 
It recursively sorts the left and right sub-arrays and concatenates the results with the middle sub-array to obtain the final sorted array. 


## Eval

**Model evaluated in 4bit** 

----Benchmark Complete----
+ 2024-01-24 15:03:08
+ Time taken: 37.4 mins
+ Prompt Format: Mistral
+ Model: macadeliccc/laser-dolphin-mixtral-4x7b-dpo
+ Score (v2): 71.04
+ Parseable: 169.0
---------------


## Citations

Fernando Fernandes Neto and Eric Hartford. "Optimizing Large Language Models Using Layer-Selective Rank Reduction and Random Matrix Theory." 2024.

```bibtex
@article{sharma2023truth,
title={The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction},
author={Sharma, Pratyusha and Ash, Jordan T and Misra, Dipendra},
journal={arXiv preprint arXiv:2312.13558},
year={2023} }
```

```bibtex
@article{gao2021framework,
  title={A framework for few-shot language model evaluation},
  author={Gao, Leo and Tow, Jonathan and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and McDonell, Kyle and Muennighoff, Niklas and others},
  journal={Version v0. 0.1. Sept},
  year={2021}
}
```
# [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_macadeliccc__laser-dolphin-mixtral-4x7b-dpo)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |66.71|
|AI2 Reasoning Challenge (25-Shot)|64.93|
|HellaSwag (10-Shot)              |85.81|
|MMLU (5-Shot)                    |63.04|
|TruthfulQA (0-shot)              |63.77|
|Winogrande (5-shot)              |77.82|
|GSM8k (5-shot)                   |44.88|