Spaetzle
Collection
German-English models, mostly merged, some sft/dpo
•
117 items
•
Updated
llama3-8b-spaetzle-v39 is a merge of the following models:
- cstr/llama3-8b-spaetzle-v38
- cstr/llama3-8b-spaetzle-v36
- cstr/llama3-8b-spaetzle-v33
- cstr/llama3-8b-spaetzle-v28
Quantised as q4km gguf, it achieves
on EQ Bench (v2_de): 65.12 (171 parseable),
on EQ Bench (v2): 73.64 (171 parseable).
Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
---|---|---|---|---|---|
llama3-8b-spaetzle-v39 | 43.43 | 73.31 | 60 | 45.89 | 55.66 |
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
arc_challenge | 0 | acc | 60.75 | ± | 1.43 |
acc_norm | 63.40 | ± | 1.41 | ||
arc_easy | 0 | acc | 85.10 | ± | 0.73 |
acc_norm | 83.46 | ± | 0.76 | ||
boolq | 1 | acc | 84.74 | ± | 0.63 |
hellaswag | 0 | acc | 62.23 | ± | 0.48 |
acc_norm | 80.73 | ± | 0.39 | ||
openbookqa | 0 | acc | 38.00 | ± | 2.17 |
acc_norm | 46.80 | ± | 2.23 | ||
piqa | 0 | acc | 79.92 | ± | 0.93 |
acc_norm | 80.25 | ± | 0.93 | ||
winogrande | 0 | acc | 73.80 | ± | 1.24 |
>>> What is 7777 + 3333?
Let's do the math:
7777 + 3333 = 11110
>>> I have 10 apples. I find 3 gold coins in the bottom of a river. The river runs near a big city that has something to
... do with what I can spend the coins on. I then lose 4 apples but gain a gold coin. Three birds run into my path and dr
... op 6 apples each. I play an online game and win 6 gold coins but I have to share them equally with my 2 teammates. I
... buy apples for all the coins I have. The price of an apple is 0.5 coins. How many apples do I have? And where is the
... river?
Let's break this down step by step!
Initially, you have 10 apples.
You find 3 gold coins in the river.
No mention of spending these coins yet.
You lose 4 apples, leaving you with 6 apples.
You gain a gold coin, so now you have 4 coins (3 + 1).
Then, three birds drop 6 apples each, which is a total of 18 apples. You now have:
6 (initial apples) + 18 (new apples) = 24 apples
In the online game, you win 6 gold coins, but since you have to share with teammates, each of you gets 2 coins (6 ÷
3). So, you gain 2 new coins.
You now have a total of 6 coins (4 initial + 2 gained).
With your 6 coins, you can buy apples at a rate of 0.5 coins per apple.
To find out how many apples you can buy, divide the number of coins by the price per apple:
6 coins ÷ 0.5 coins/apple = 12 apples
So, after buying apples with all your coins, you have a total of 24 (initial) + 12 (new) = 36 apples.
As for where the river is, it runs near a big city that has something to do with spending gold coins. Since you
bought apples with your coins, we can infer that this city might be a market or a place where fruits and goods are
sold. However, the exact location of the river is not specified in the story.
>>> Two years ago, I was three times as old as my brother was. In three years, I will be twice as old as my brother. How
... old is each of us now?
...
Let's use variables to represent the current ages:
* My current age = M
* My brother's current age = B
Two years ago, the equation would be:
M - 2 = 3(B - 2)
Since I was three times as old as my brother two years ago, we can simplify the equation:
M - 2 = 3B - 6
M = 3B - 4
Now, let's look at the future situation in three years:
M + 3 = 2(B + 3)
Expanding and simplifying:
M + 3 = 2B + 6
M = 2B + 3
We now have two equations with two variables:
1) M = 3B - 4
2) M = 2B + 3
Equating the right sides of these equations, we get:
3B - 4 = 2B + 3
Simplifying and solving for B (my brother's current age):
B = 7
Now that we know my brother's current age, we can find mine:
M = 3B - 4
= 3(7) - 4
= 21 - 4
= 17
So, I am currently 17 years old, and my brother is currently 7 years old.
models:
- model: cstr/llama3-8b-spaetzle-v33
- model: cstr/llama3-8b-spaetzle-v38
- model: cstr/llama3-8b-spaetzle-v36
- model: cstr/llama3-8b-spaetzle-v28
merge_method: model_stock
base_model: cstr/llama3-8b-spaetzle-v33
dtype: bfloat16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "cstr/llama3-8b-spaetzle-v39"
messages = [{"role": "user", "content": "What is a large language model?"}]
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"])