MaxiCPM-3x3B-Test
MaxiCPM-3x3B-Test is a Mixure of Experts (MoE) made with the following models using LazyMergekit:
- indischepartij/MiniCPM-3B-Hercules-v2.0
- indischepartij/MiniCPM-3B-OpenHermes-2.5-v2
- indischepartij/MiniCPM-3B-Bacchus
🧩 Configuration
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
!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
Detailed results can be found here
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 |
- Downloads last month
- 61
Inference API (serverless) is not available, repository is disabled.
Model tree for gmonsoon/MaxiCPM-3x3B-Test
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard45.990
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard71.740
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard52.880
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard41.060
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard66.850
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard44.880