|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- yahma/alpaca-cleaned |
|
metrics: |
|
- accuracy |
|
base_model: |
|
- meta-llama/Meta-Llama-3.1-8B-Instruct |
|
--- |
|
## Usage |
|
Support for this model will be added in the upcoming transformers release. In the meantime, please install the library from source: |
|
~~~ |
|
pip install transformers |
|
~~~ |
|
We can now run inference on this model: |
|
~~~ |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
# Load the tokenizer and model |
|
model_path = "YaoLuzjut/Llama-3.1-6.3B-It-Alpaca" |
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
|
|
device = 'cuda' |
|
dtype = torch.bfloat16 |
|
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device) |
|
|
|
# Prepare the input text |
|
prompt = 'Complete the paragraph: our solar system is' |
|
inputs = tokenizer.encode(prompt, return_tensors='pt').to(model.device) |
|
|
|
# Generate the output |
|
outputs = model.generate(inputs, max_length=20) |
|
|
|
# Decode and print the output |
|
output_text = tokenizer.decode(outputs[0]) |
|
print(output_text) |
|
~~~ |
|
|
|
## Evaluation Results |
|
Zero-shot performance. Evaluated using select datasets from the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/main) with additions: |
|
| PIQA | HellaSwag | OpenbookQA | ARC-e | ARC-c | MMLU | CMMLU | WinoGrande | |
|
| ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | |
|
| 0.7383±0.0103 | 0.5323±0.0050 | 0.3080±0.0207 | 0.7260±0.0092 | 0.4684±0.0146 | 0.6567±0.0038 | 0.5515±0.0045 | 0.6646±0.0133 | |
|
|
