DrKlaus-7B

DrKlaus-7B is a SFT model made with AutoSloth by macadeliccc

Process

• Original Model: mistralai/Mistral-7B-Instruct-v0.2

• Datatset: medalpaca/medical_meadow_wikidoc_patient_information

• Learning Rate: 3e-05

• Steps: 80

• Warmup Steps: 8

• Per Device Train Batch Size: 24

• Gradient Accumulation Steps 12

• Optimizer: adamw_8bit

• Max Sequence Length: 1024

• Max Prompt Length: 512

• Max Length: 1024

💻 Usage

!pip install -qU transformers

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

model = "macadeliccc/DrKlaus-7B"
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"])