phi-3-mini-4k-instruct-prune2 is a merge of the following models using
LazyMergekit:
1dtype: bfloat16
2merge_method: passthrough
3slices:
4- sources:
5 - layer_range: [0, 25]
6 model: microsoft/Phi-3-mini-4k-instruct
7- sources:
8 - layer_range: [31, 32]
9 model: microsoft/Phi-3-mini-4k-instruct
1!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "aipib/phi-3-mini-4k-instruct-prune2"
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"])
