Tinyllama-moe1

Tinyllama-moe1 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"
    - "explain"
  - source_model: phanerozoic/Tiny-Pirate-1.1b-v0.1
    positive_prompts:
    - "storywriting"
    - "scene"
    - "story"
  - source_model: Tensoic/TinyLlama-1.1B-3T-openhermes
    positive_prompts:
    - "reason"
    - "instruct"
    - "count"

πŸ’» Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "aipib/Tinyllama-moe1"

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"])
Downloads last month
109
Safetensors
Model size
2.62B params
Tensor type
FP16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for aipib/Tinyllama-moe1