---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- indischepartij/MiniCPM-3B-Hercules-v2.0
- indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
- indischepartij/MiniCPM-3B-Bacchus
base_model:
- indischepartij/MiniCPM-3B-Hercules-v2.0
- indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
- indischepartij/MiniCPM-3B-Bacchus
model-index:
- name: MaxiCPM-3x3B-Test
  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: 45.99
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/MaxiCPM-3x3B-Test
      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: 71.74
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/MaxiCPM-3x3B-Test
      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: 52.88
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/MaxiCPM-3x3B-Test
      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: 41.06
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/MaxiCPM-3x3B-Test
      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: 66.85
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/MaxiCPM-3x3B-Test
      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=gmonsoon/MaxiCPM-3x3B-Test
      name: Open LLM Leaderboard
---

# MaxiCPM-3x3B-Test

MaxiCPM-3x3B-Test is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [indischepartij/MiniCPM-3B-Hercules-v2.0](https://huggingface.co/indischepartij/MiniCPM-3B-Hercules-v2.0)
* [indischepartij/MiniCPM-3B-OpenHermes-2.5-v2](https://huggingface.co/indischepartij/MiniCPM-3B-OpenHermes-2.5-v2)
* [indischepartij/MiniCPM-3B-Bacchus](https://huggingface.co/indischepartij/MiniCPM-3B-Bacchus)

## 🧩 Configuration

```yaml
base_model: openbmb/MiniCPM-2B-dpo-bf16-llama-format
experts:
  - source_model: indischepartij/MiniCPM-3B-Hercules-v2.0
    positive_prompts:
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
  - source_model: indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
    positive_prompts:
    - "code"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
  - source_model: indischepartij/MiniCPM-3B-Bacchus
    positive_prompts:
    - "storywriting"
    - "write"
    - "scene"
    - "story"
    - "character"
    - "reason"
    - "math"
    - "mathematics"
    - "solve"
    - "count"
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gmonsoon/MaxiCPM-3x3B-Test"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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_gmonsoon__MaxiCPM-3x3B-Test)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |53.90|
|AI2 Reasoning Challenge (25-Shot)|45.99|
|HellaSwag (10-Shot)              |71.74|
|MMLU (5-Shot)                    |52.88|
|TruthfulQA (0-shot)              |41.06|
|Winogrande (5-shot)              |66.85|
|GSM8k (5-shot)                   |44.88|