i2xmortal/Immortal-phi-3-experts-instruct

---

license: apache-2.0

🧩 Configuration

base_model: microsoft/Phi-3-mini-4k-instruct
gate_mode: cheap_embed
experts_per_token: 1
dtype: float16
experts:
  - source_model: microsoft/Phi-3-mini-4k-instruct
    positive_prompts: ["If the user asks about your name you should say my name is expert1"]
  - source_model: microsoft/Phi-3-mini-4k-instruct
    positive_prompts: ["If the user asks about 'how are you', you should say as 'expert2 im very fine'"]

💻 Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = "i2xmortal/Phi3Mix"

tokenizer = AutoTokenizer.from_pretrained(model)

model = AutoModelForCausalLM.from_pretrained(
    model,
    trust_remote_code=True,
)

prompt="How many continents are there?"
input = f"<|system|>You are a helpful AI assistant.<|end|><|user|>{prompt}<|assistant|>"
tokenized_input = tokenizer.encode(input, return_tensors="pt")

outputs = model.generate(tokenized_input, max_new_tokens=128, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(tokenizer.decode(outputs[0]))