Downloads · 30 days
81
4% of all-time downloads
RichardErkhov/saucam_-_aqua-smaug-0.3-8B-gguf
saucam_-_aqua-smaug-0.3-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
81
4% of all-time downloads
All-time downloads
2.2K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
aqua-smaug-0.3-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| aqua-smaug-0.3-8B.Q2_K.gguf | Q2_K | 2.96GB |
| aqua-smaug-0.3-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| aqua-smaug-0.3-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| aqua-smaug-0.3-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| aqua-smaug-0.3-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| aqua-smaug-0.3-8B.Q3_K.gguf | Q3_K | 3.74GB |
| aqua-smaug-0.3-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| aqua-smaug-0.3-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| aqua-smaug-0.3-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| aqua-smaug-0.3-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| aqua-smaug-0.3-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| aqua-smaug-0.3-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| aqua-smaug-0.3-8B.Q4_K.gguf | Q4_K | 4.58GB |
| aqua-smaug-0.3-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| aqua-smaug-0.3-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| aqua-smaug-0.3-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| aqua-smaug-0.3-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| aqua-smaug-0.3-8B.Q5_K.gguf | Q5_K | 5.34GB |
| aqua-smaug-0.3-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| aqua-smaug-0.3-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| aqua-smaug-0.3-8B.Q6_K.gguf | Q6_K | 6.14GB |
| aqua-smaug-0.3-8B.Q8_0.gguf | Q8_0 | 7.95GB |
tags:

aqua-smaug-0.3-8B is a merge of the following models using Mergekit:
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
| 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
!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%|███████████████████████████████████████████████████| 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. 😊
### References
- [Carnival Booth Earnings Calculation](https://www.calculator.net/calculators/math/equation-calculator.html) (for verifying calculations)
- [Cotton Candy