Views
No views yet
Important!: Currently, this model has not undergone CPT (Continued Pre-Training) following the merge; it will be replaced later with a CPT-processed version.
pfnet/plamo-3-nict-8b-base and scaling it up to 12B parameters.This is a merge of pre-trained language models created using mergekit.
python>=3.10.0
numpy>=1.26.4
numba>=0.60.0
torch>=2.6.0,<=2.9.0
transformers>=4.56.0,<=4.57.11from transformers import AutoTokenizer, AutoModelForCausalLM
2
3model_id = "midorin-Linux/plamo-3-12b-self-merged"
4
5tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
6model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
7
8text = "これからの人工知能技術は"
9inputs = tokenizer(text, return_tensors="pt").to(model.device)
10
11generated_tokens = model.generate(
12 **inputs,
13 max_new_tokens=32,
14 do_sample=True,
15 top_k=50,
16 top_p=0.95,
17 temperature=1.0,
18 pad_token_id=tokenizer.eos_token_id,
19 use_cache=True,
20)[0]
21
22generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
23print(generated_text)