Qwen2-2x1.5B

Qwen2-2x1.5B is a Mixture of Experts (MoE) made with the following models using LazyMergekit:

• cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
• macadeliccc/Samantha-Qwen2-1.5B

🧩 Configuration

base_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
gate_mode: hidden
architecture: qwen
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
    positive_prompts:
    - "chat"
    - "assistant"
    - "explain"
    - "describe"
    - "define"
    - "what is"
    - "tell me"
    - "help me"
    - "show me"
    - "can you"
  - source_model: macadeliccc/Samantha-Qwen2-1.5B
    positive_prompts:
    - "characters"
    - "scene"
    - "roleplay"
    - "writing"
    - "creative"
    - "you are"
    - "act as"
shared_experts:
  - source_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
    positive_prompts: # required by Qwen MoE for "hidden" gate mode, otherwise not allowed
      - "chat"
      - "assistant"
    # (optional, but recommended:)
    residual_scale: 0.1

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "djuna/Qwen2-2x1.5B"

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"])