|
--- |
|
base_model: |
|
- meta-llama/Llama-3.2-1B-Instruct |
|
datasets: |
|
- fineinstructions/templates_raw_subsample |
|
tags: |
|
- datadreamer |
|
- datadreamer-0.39.0 |
|
- synthetic |
|
- text-generation |
|
widget: |
|
- text: >+ |
|
<|start_header_id|>system<|end_header_id|> |
|
|
|
|
|
Cutting Knowledge Date: December 2023 |
|
|
|
Today Date: 31 Jan 2025 |
|
|
|
|
|
<|eot_id|><|start_header_id|>user<|end_header_id|> |
|
|
|
|
|
What volleyball exercises should I do I'm almost in high school and i do |
|
volleyball excellence five times a week (basically an advanced class in |
|
school with experienced volleyball coaches) , we have 2-3 skill training |
|
sessions a week which i feel like isn't enough for me as I would like to |
|
improve my skills almost every day. |
|
|
|
|
|
&#x200B; |
|
|
|
|
|
What i wanted to know was what setting, digging, serving and spiking |
|
exercises could i do that would help me improve all of my skills (I have a |
|
large area to practice all these things so space isn't an |
|
issue).<|eot_id|><|start_header_id|>assistant<|end_header_id|> |
|
|
|
example_title: Example 1 |
|
- text: >+ |
|
<|start_header_id|>system<|end_header_id|> |
|
|
|
|
|
Cutting Knowledge Date: December 2023 |
|
|
|
Today Date: 31 Jan 2025 |
|
|
|
|
|
<|eot_id|><|start_header_id|>user<|end_header_id|> |
|
|
|
|
|
 |
|
|
|
|
|
Hi i am trying to make java desktop application where i am using `JLabel` I |
|
wrote some test on `JLabel` I want to set text from the top and I am using |
|
multiple line in `JLabel` I want to set different different color for every |
|
line. |
|
|
|
|
|
Here is my code: |
|
|
|
|
|
``` |
|
|
|
JLabel label = new JLabel("<html>Case |
|
Item |
|
CaseNum<br>Party1<br>Party2</html>"); |
|
|
|
|
|
``` |
|
|
|
|
|
How can I achieve |
|
this?<|eot_id|><|start_header_id|>assistant<|end_header_id|> |
|
|
|
example_title: Example 2 |
|
- text: >+ |
|
<|start_header_id|>system<|end_header_id|> |
|
|
|
|
|
Cutting Knowledge Date: December 2023 |
|
|
|
Today Date: 31 Jan 2025 |
|
|
|
|
|
<|eot_id|><|start_header_id|>user<|end_header_id|> |
|
|
|
|
|
Is there a cheaper substitute for the knipex pliers? I have wanted a pair of |
|
the knipex crimpers/pliers/cutters for a while, but I can't afford $70 for a |
|
pair. Is there a pair that is as good, but |
|
cheaper?<|eot_id|><|start_header_id|>assistant<|end_header_id|> |
|
|
|
example_title: Example 3 |
|
pipeline_tag: text-generation |
|
--- |
|
# Model Card |
|
|
|
[Add more information here](https://huggingface.co/templates/model-card-example) |
|
|
|
## Example Usage |
|
|
|
```python3 |
|
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, Conversation |
|
|
|
tokenizer = AutoTokenizer.from_pretrained('fineinstructions/query_templatizer', revision=None) # Load tokenizer |
|
tokenizer.padding_side = 'left' |
|
model = AutoModelForCausalLM.from_pretrained('fineinstructions/query_templatizer_full_end_to_end_s2', revision=None) # Load model |
|
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, pad_token_id=tokenizer.pad_token_id, return_full_text=False) |
|
|
|
inputs = ["What volleyball exercises should I do I'm almost in high school and i do volleyball excellence five times a week (basically an advanced class in school with experienced volleyball coaches) , we have 2-3 skill training sessions a week which i feel like isn't enough for me as I would like to improve my skills almost every day.\n\n&#x200B;\n\nWhat i wanted to know was what setting, digging, serving and spiking exercises could i do that would help me improve all of my skills (I have a large area to practice all these things so space isn't an issue)."] |
|
prompts = [tokenizer.apply_chat_template([{'role': 'user', 'content': i}], tokenize=False, add_generation_prompt=True) for i in inputs] |
|
print(pipe(prompts, max_length=131072, do_sample=False)) |
|
``` |
|
|
|
--- |
|
This model was trained with a synthetic dataset with [DataDreamer 🤖💤](https://datadreamer.dev). The synthetic dataset card and model card can be found [here](datadreamer.json). The training arguments can be found [here](training_args.json). |
