|
--- |
|
license: apache-2.0 |
|
metrics: |
|
- accuracy |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Summary |
|
|
|
"Deer-3b," an instruction-following large language model based on "Bloom-3b," is fine-tuned using ±5k instructions. |
|
|
|
Deer will also be available in larger models size. |
|
|
|
## Usage |
|
|
|
To use the model with the `transformers` library on a machine with GPUs. |
|
|
|
```python |
|
import torch |
|
from transformers import pipeline |
|
generate_text = pipeline(model="PSanni/Deer-3b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto") |
|
``` |
|
|
|
You can then use the pipeline to answer instructions: |
|
|
|
```python |
|
res = generate_text("Explain to me the difference between nuclear fission and fusion.") |
|
print(res[0]["generated_text"]) |
|
``` |
|
|
|
### Note: |
|
|
|
Kindly note that the model isn't attuned to human preferences and could generate unsuitable, unethical, biased, and toxic responses. |
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PSanni__Deer-3b) |
|
|
|
| Metric | Value | |
|
|-----------------------|---------------------------| |
|
| Avg. | 32.01 | |
|
| ARC (25-shot) | 38.48 | |
|
| HellaSwag (10-shot) | 57.41 | |
|
| MMLU (5-shot) | 25.64 | |
|
| TruthfulQA (0-shot) | 39.98 | |
|
| Winogrande (5-shot) | 57.46 | |
|
| GSM8K (5-shot) | 0.3 | |
|
| DROP (3-shot) | 4.83 | |
|
|
