SvalTek/Q2.5-ColdBrew-RxV

name: Q2.5-ColdBrew-RxV

base_model: SvalTek/Q2.5-ColdBrew-RxB
models:
  - model: SvalTek/Q2.5-ColdBrew-Rx
  - model: SvalTek/Q2.5-ColdBrew-R1-Aspera
  - model: SvalTek/Qwen2.5-ColdBrew-Apartide

merge_method: model_stock
tokenizer_source: SvalTek/Q2.5-ColdBrew-RxB
dtype: bfloat16
normalize: true
int8_mask: true

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "SvalTek/Q2.5-ColdBrew-RxV"
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"])