README.md

metadata

base_model:
  - bunnycore/HyperLlama-3.1-8B
  - Quazim0t0/Aura-8B-Linear
  - Quazim0t0/LR-Tensors
tags:
  - merge
  - mergekit
  - lazymergekit
  - bunnycore/HyperLlama-3.1-8B
  - Quazim0t0/Aura-8B-Linear
  - Quazim0t0/LR-Tensors

Charlie-8B-Linear

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

• bunnycore/HyperLlama-3.1-8B
• Quazim0t0/Aura-8B-Linear
• Quazim0t0/LR-Tensors

🧩 Configuration

models:
  - model: bunnycore/HyperLlama-3.1-8B
    parameters:
      weight: 1.5
  - model: Quazim0t0/Aura-8B-Linear
    parameters:
      weight: 1.2
  - model: Quazim0t0/LR-Tensors
    parameters:
      weight: 1.2

merge_method: linear
normalize: false
int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Quazim0t0/Charlie-8B-Linear"
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"])