Experimenting-Test4.5-8B-2

Experimenting-Test4.5-8B-2 is a merge of the following models using LazyMergekit:

• Kaoeiri/Experimenting-Test3.5-8B-2
• cgato/L3-TheSpice-8b-v0.1.3
• Sao10K/L3-Solana-8B-v1

🧩 Configuration

models:
      - model: Kaoeiri/Experimenting-Test3.5-8B-2
        parameters:
           density: .76
           weight: .64
      - model: cgato/L3-TheSpice-8b-v0.1.3
        parameters:
           density: .366
           weight: .4
      - model: Sao10K/L3-Solana-8B-v1
        parameters:
           density: .4
           weight: .46
merge_method: model_stock
base_model: cgato/L3-TheSpice-8b-v0.1.3
parameters:
  normalize: true
  int8_mask: true
  
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kaoeiri/Experimenting-Test4.5-8B-2"
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=0.9, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])