metadata
tags:
- merge
- mergekit
- cognitivecomputations/dolphin-2.9-llama3-8b
- abacusai/Llama-3-Smaug-8B
- meta-llama/Meta-Llama-3-8B
base_model:
- cognitivecomputations/dolphin-2.9-llama3-8b
- abacusai/Llama-3-Smaug-8B
- meta-llama/Meta-Llama-3-8B
license: apache-2.0
π¦ aqua-smaug-0.3-8B π
aqua-smaug-0.3-8B is a merge of the following models using Mergekit:
𧩠Configuration
models:
- model: cognitivecomputations/dolphin-2.9-llama3-8b
- model: abacusai/Llama-3-Smaug-8B
- model: meta-llama/Meta-Llama-3-8B
merge_method: model_stock
base_model: abacusai/Llama-3-Smaug-8B
dtype: bfloat16
Eval Results
Benchmark | Model | winogrande | arc | gsm8k | mmlu | truthfulqa | hellaswag | Average |
---|---|---|---|---|---|---|---|---|
openllm | aqua-smaug-0.3-8B | 77.11 | 62.37 | 76.19 | 66 | 53.7 | 83.02 | 69.73 |
Detailed Results: https://github.com/saucam/model_evals/tree/main/saucam/aqua-smaug-0.3-8B
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "saucam/aqua-smaug-0.3-8B"
messages = [{"role": "user", "content": "A carnival snack booth made $50 selling popcorn each day. It made three times as much selling cotton candy. For a 5-day activity, the booth has to pay $30 rent and $75 for the cost of the ingredients. How much did the booth earn for 5 days after paying the rent and the cost of ingredients? How much did the booth make selling cotton candy each day?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
output
Loading checkpoint shards: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββ| 2/2 [00:27<00:00, 13.83s/it]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
A carnival snack booth made $50 selling popcorn each day. It made three times as much selling cotton candy. For a 5-day activity, the booth has to pay $30 rent and $75 for the cost of the ingredients. How much did the booth earn for 5 days after paying the rent and the cost of ingredients? How much did the booth make selling cotton candy each day?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
The carnival snack booth made $50 selling popcorn each day. Since it made three times as much selling cotton candy, it made $50 * 3 = $150 each day selling cotton candy.
For a 5-day activity, the booth made $50 * 5 = $250 selling popcorn and $150 * 5 = $750 selling cotton candy.
The booth has to pay $30 rent and $75 for the cost of the ingredients for 5 days, which is a total of $30 + $75 = $105.
After paying the rent and the cost of ingredients, the booth earned $250 + $750 - $105 = $895 for 5 days.
Therefore, the booth made $150 each day selling cotton candy.
So, the total amount earned by selling popcorn is $250 and by selling cotton candy is $750. After deducting the rent and cost of ingredients, the booth earned a total of $895 for the 5-day activity.
Hope this helps! Let me know if you have any more questions. π
### References
- [Carnival Booth Earnings Calculation](https://www.calculator.net/calculators/math/equation-calculator.html) (for verifying calculations)
- [Cotton Candy