pantelnm/llama3-openassistant

Model Details

This model is a finetuned Meta-Llama-3-8b-Instruct model on the openassistant dataset. It was finetuned using PEFT, a library for efficiently adapting pre-trained language models to various downstream applications without fine-tuning all the model’s parameters.

Inference with PEFT Models:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig

base_model = "meta-llama/Meta-Llama-3-8B"
adapter_model = "pantelnm/llama3-openassistant"

prompt = "Write your prompt here!"

model = AutoModelForCausalLM.from_pretrained(base_model)
model = PeftModel.from_pretrained(model, adapter_model)
tokenizer = AutoTokenizer.from_pretrained(base_model)

model = model.to("cuda")
model.eval()

inputs = tokenizer(prompt, return_tensors="pt")

with torch.no_grad():
    outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=10)
    print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0])

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

General Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "PATH_TO_THIS_REPO"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)