ColdBrew-12B-NemoMix-test0

🧩 Configuration

name: ColdBrew-12B-NemoMix-test0

models:
  - model: mergekit-community/mergekit-task_arithmetic-zxjskqt
  - model: elinas/Chronos-Gold-12B-1.0

base_model: "LatitudeGames/Wayfarer-12B"
chat_template: "chatml"
merge_method: "model_stock"
tokenizer_source: base
dtype: bfloat16
normalize: true
int8_mask: true

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "SvalTek/ColdBrew-12B-NemoMix-test0"
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"])