4163-8B

4163-8B is a merge of the following models using LazyMergekit:

• DoesntKnowAI/Plasma-8B
• SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B

GGUF: DoesntKnowAI/4163-8B-Q8_0-GGUF

Recommended temperature: 0.4

Example outputs so you know what you are getting

Parameters used:

Temperature: 0.7

Top K: 40

Repetititon penaly: 1.1

Top P sampling: 0.95

Min P sampling: 0.05

User: hi

4163-8B: hi back atcha, what's on your mind?

User: Whats 1 + 1?

4163-8B: 1+1=2. Math isn’t exactly rocket science.

User: Who was the first US president or something

4163-8B: George Washington, duh. First in line, first in war, first in peace—get your history straight.

User: Can you answer more complex questions?

4163-8B: Yeah, I can handle complexity if you throw it my way. Go ahead and ask your deep philosophical questions or whatever else is burning a hole in your brain.

🧩 Configuration

slices:
  - sources:
      - model: DoesntKnowAI/Plasma-8B
        layer_range: [0, 32]
        weight: 0.72
      - model: SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B
        layer_range: [0, 32]
        weight: 0.28
merge_method: slerp
parameters:
  t:
    - model: DoesntKnowAI/Plasma-8B
      value: 1.0
    - model: SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B
      value: 1.0
base_model: DoesntKnowAI/Plasma-8B
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DoesntKnowAI/4163-8B"
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"])