README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - jeiku/Average_Normie_l3_v1_8B
  - Kaoeiri/Keiana-L3-Test4.6-8B-2
base_model:
  - jeiku/Average_Normie_l3_v1_8B
  - Kaoeiri/Keiana-L3-Test4.6-8B-2

Keiana-L3-Test4.7-8B-3

Keiana-L3-Test4.7-8B-3 is a merge of the following models using LazyMergekit:

• jeiku/Average_Normie_l3_v1_8B
• Kaoeiri/Keiana-L3-Test4.6-8B-2

🧩 Configuration

merge_method: task_arithmetic
dtype: float16
base_model: ResplendentAI/SOVL_Llama3_8B
models:
  - model: jeiku/Average_Normie_l3_v1_8B
    parameters:
      weight: 1.0
  - model: Kaoeiri/Keiana-L3-Test4.6-8B-2
    parameters:
      weight: 1.0

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kaoeiri/Keiana-L3-Test4.7-8B-3"
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"])