README.md

---
license: cc-by-nc-4.0
tags:
- moe
- dpo
model-index:
- name: Mixtral_7Bx2_MoE_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: 73.04
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE_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: 88.76
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE_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: 64.94
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE_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: 81.5
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE_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: 82.16
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE_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: 64.9
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_7Bx2_MoE_DPO
      name: Open LLM Leaderboard
---

# DPO of cloudyu/Mixtral_7Bx2_MoE

dataset : jondurbin/truthy-dpo-v0.1 

* metrics average 75.88 
* TruthfulQA 81.5 SOTA (2024-01-17)

gpu code example

```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math

## v2 models
model_path = "cloudyu/Mixtral_7Bx2_MoE_DPO"

tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.bfloat16, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")

  generation_output = model.generate(
    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
  )
  print(tokenizer.decode(generation_output[0]))
  prompt = input("please input prompt:")
```



# [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_cloudyu__Mixtral_7Bx2_MoE_DPO)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |75.88|
|AI2 Reasoning Challenge (25-Shot)|73.04|
|HellaSwag (10-Shot)              |88.76|
|MMLU (5-Shot)                    |64.94|
|TruthfulQA (0-shot)              |81.50|
|Winogrande (5-shot)              |82.16|
|GSM8k (5-shot)                   |64.90|