|
--- |
|
library_name: transformers |
|
tags: |
|
- llm |
|
- 7b |
|
license: cc-by-4.0 |
|
language: |
|
- en |
|
datasets: |
|
- argilla/distilabel-math-preference-dpo |
|
--- |
|
|
|
# Jaskier-7b-dpo-v5.6 |
|
|
|
**This is work-in-progress model, may not be ready for production use** |
|
|
|
Model based on `paulml/OGNO-7B` (downstream version of Mistral7B) finetuned using Direct Preference Optimization on argilla/distilabel-math-preference-dpo. |
|
|
|
## How to use |
|
|
|
You can use this model directly with a Hugging Face pipeline: |
|
```python |
|
import ... |
|
|
|
base_model_name = "bardsai/jaskier-7b-dpo-v5.6" |
|
p = pipeline("conversational", model=base_model_name, torch_dtype=torch.float16, device_map="auto") |
|
messages = [{'messages':[{ |
|
"role": "user", |
|
"content": "Can Poland into space?" |
|
}]}, |
|
{'messages':[{ |
|
"role": "user", |
|
"content": "Tell me where the nearest water park is?" |
|
}]}, |
|
] |
|
|
|
def conversations(): |
|
for x in tqdm(messages): |
|
yield Conversation(x['messages']) |
|
|
|
generate_kwargs = { |
|
"do_sample": True, |
|
"temperature": 0.7, |
|
"max_new_tokens": 1024, |
|
} |
|
model_outputs = [out[-1]['content'] for out in p(conversations(), **generate_kwargs)] |
|
|
|
print(model_outputs) |
|
|
|
``` |
|
|
|
## Output |
|
|
|
>["Poland, as a nation, invests in and collaborates with the international space community, primarily through the Polish Space Agency and the Institute of Space Physics of the Polish Academy of Sciences. They don't physically send Poland to space, but work on advances, technology, and scientific research related to space exploration."] |
|
>["As an AI, I don't have real-time physical location or personal experiences. I can't provide location-specific information. Please, consider asking a fellow human for such details."] |
|
|
|
If you still find any issues with "INST" character chain appearing in generated output, try our newest model: https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1 . Re-tasking the prompt can also help. |
|
## Changelog |
|
|
|
- 2024-02-16: Initial release |
|
|
|
## About bards.ai |
|
|
|
At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: bards.ai |
|
|
|
Let us know if you use our model :). Also, if you need any help, feel free to contact us at info@bards.ai |
