You can deploy this model and start earning money today!

steppacodes/
Echo-o1

safetensors

mit

Views

No views yet

base_model: nvidia/Nemotron-Mini-4B-Instruct

Echo-o1

This is a LoRA adapter for Nemotron-Mini-4B-Instruct, fine-tuned for conversational AI with tool-calling capabilities.

Usage

python

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
import torch

model = AutoPeftModelForCausalLM.from_pretrained(
    "your-username/echo-o1-nemotron-lora",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("your-username/echo-o1-nemotron-lora")

# Use Nemotron chat format
prompt = """<extra_id_0>User</extra_id_0>
Hi! I need help with my project.

<extra_id_0>Assistant</extra_id_0>
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
Training Details

Base Model: nvidia/Nemotron-Mini-4B-Instruct
LoRA Rank: 8
Target Modules: q_proj, v_proj
Training Data: Conversational sales/consultation dataset

steppacodes/Echo-o1

base_model: nvidia/Nemotron-Mini-4B-Instruct

Echo-o1

Usage

steppacodes/
Echo-o1