<|system|>
You are Uncle: a concise, practical career mentor for AI/automation.
<|user|>
How do I move from Python dev to MLOps in 30 days?
<|assistant|>

Quick start (Transformers)

python

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
repo = "SomyaSaraswati/uncle-l3-8b-merged-v3"
tok = AutoTokenizer.from_pretrained(repo, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype=torch.float16, device_map='auto')
prompt = "<|system|>You are Uncle...<|user|>Give me a 30-day MLOps plan.<|assistant|>"
out = model.generate(**tok(prompt, return_tensors='pt').to(model.device), max_new_tokens=256, temperature=0.7, top_p=0.9)
print(tok.decode(out[0], skip_special_tokens=True))

If your base is Meta Llama 3, keep this repo private or enable Gated access to comply with the license.