README.md

metadata

license: apache-2.0

Opus-Samantha-Llama-3-8B

Opus-Samantha-Llama-3-8B is a SFT model made with AutoSloth by macadeliccc

Process

• Original Model: unsloth/llama-3-8b

• Datatset: macadeliccc/opus_samantha

• Learning Rate: 2e-05

• Steps: 2772

• Warmup Steps: 277

• Per Device Train Batch Size: 2

• Gradient Accumulation Steps 1

• Optimizer: paged_adamw_8bit

• Max Sequence Length: 4096

• Max Prompt Length: 2048

• Max Length: 2048

💻 Usage

!pip install -qU transformers

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

model = "macadeliccc/Opus-Samantha-Llama-3-8B"
tokenizer = AutoTokenizer.from_pretrained(model)

# Example prompt
prompt = "Your example prompt here"

# Generate a response
model = AutoModelForCausalLM.from_pretrained(model)
pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
outputs = pipeline(prompt, max_length=50, num_return_sequences=1)
print(outputs[0]["generated_text"])