AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T

base_model: ahxt/LiteLlama-460M-1T
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: ahxt/LiteLlama-460M-1T
    positive_prompts: ["Accounting"]
  - source_model: ahxt/LiteLlama-460M-1T
    positive_prompts: ["Finance"]
  - source_model: ahxt/LiteLlama-460M-1T
    positive_prompts: ["Strategy"]
  - source_model: ahxt/LiteLlama-460M-1T
    positive_prompts: ["Marketing"]
  - source_model: ahxt/LiteLlama-460M-1T
    positive_prompts: ["Organizational Behaviour"]
  - source_model: ahxt/LiteLlama-460M-1T
    positive_prompts: ["Economics"]

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T"

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"])