ColdBrew-12B-Nemo-test2

ColdBrew-12B-Nemo-test2

🧩 Configuration

name: ColdBrew-12B-Nemo-test2

models:
  - model: SvalTek/ColdBrew-12B-Nemo-test1
    parameters:
      weight: 1.0
  - model: elinas/Chronos-Gold-12B-1.0
    parameters:
      weight: 0.3

base_model: SvalTek/ColdBrew-12B-Nemo-test1
merge_method: task_arithmetic
chat_template: "chatml"
tokenizer:
  source: union          # keep everyone’s vocab; union is a documented option
  tokens:
    "<|im_start|>":
      source: "elinas/Chronos-Gold-12B-1.0"
      force: true
    "<|im_end|>":
      source: "elinas/Chronos-Gold-12B-1.0"
      force: true
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-Nemo-test2"
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"])