Tinyllama-moe4
Tinyllama-moe4 is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
🧩 Configuration
base_model: vihangd/DopeyTinyLlama-1.1B-v1
experts:
- source_model: vihangd/DopeyTinyLlama-1.1B-v1
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- source_model: gardner/TinyLlama-1.1B-Instruct-3T
positive_prompts:
- "reason"
- "provide"
- "instruct"
- "summarize"
- "count"
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "aipib/Tinyllama-moe4"
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"])