DeepSeek-7B-1M is a merge of the following models using
LazyMergekit:
1models:
2 - model: Qwen/Qwen2.5-7B-Instruct-1M
3 parameters:
4 weight: 0.5
5 - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
6 parameters:
7 weight: 0.5
8merge_method: linear
9dtype: float16
1!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "yasserrmd/DeepSeek-7B-1M"
8messages = [{"role": "user", "content": "What is a large language model?"}]
9
10tokenizer = AutoTokenizer.from_pretrained(model)
11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
12pipeline = transformers.pipeline(
13 "text-generation",
14 model=model,
15 torch_dtype=torch.float16,
16 device_map="auto",
17)
18
19outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
20print(outputs[0]["generated_text"])
