L3-ColdBrew-Astrid

L3-ColdBrew-Astrid is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: SvalTek/ColdBrew-Lucid+Etherll/llama3.1-8b-reflection-lora
  - model: cgato/L3-TheSpice-8b-v0.8.3+Azazelle/L3-Daybreak-8b-lora
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS+DreadPoor/Everything-COT-8B-r128-LoRA
  - model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
merge_method: model_stock
base_model: SvalTek/ColdBrew-Lucid
normalize: false
int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "SvalTek/L3-ColdBrew-Astrid"
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"])