EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT

pip install transformers torch
pip install accelerate
pip install -U transformers

from transformers import AutoTokenizer, AutoModelForCausalLM  

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT")  
model = AutoModelForCausalLM.from_pretrained("EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT")  

prompt = "Calculate the molar mass of sulfuric acid (H₂SO₄)."  
inputs = tokenizer(prompt, return_tensors="pt")  
outputs = model.generate(**inputs, max_length=200)  
print(tokenizer.decode(outputs[0], skip_special_tokens=True))


##advance inference
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT")

# Load the model in 8-bit precision using bitsandbytes (requires a CUDA GPU)
model = AutoModelForCausalLM.from_pretrained(
    "EpistemeAI/Fireball-R1-Llama-3.1-8B",
    load_in_8bit=True,      # Enable 8-bit loading to reduce memory usage
    device_map="auto"       # Automatically map model layers to the available device(s)
)

# Define the system prompt and the user prompt
system_prompt = "You are a highly knowledgeable assistant with expertise in chemistry and physics. <think>"
user_prompt = "Calculate the molar mass of sulfuric acid (H₂SO₄)."

# Combine the system prompt with the user prompt. The format here follows a common convention for chat-like interactions.
full_prompt = f"System: {system_prompt}\nUser: {user_prompt}\nAssistant:"

# Tokenize the combined prompt and move the inputs to the GPU
inputs = tokenizer(full_prompt, return_tensors="pt").to("cuda")

# Generate output text from the model
outputs = model.generate(**inputs, max_length=12200)

# Decode and print the result, skipping special tokens
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)