模型:
cyberagent/open-calm-3b
OpenCALM是由CyberAgent开发的一套基于解码器的语言模型,预训练于日本数据集。
import torch from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("cyberagent/open-calm-3b", device_map="auto", torch_dtype=torch.float16) tokenizer = AutoTokenizer.from_pretrained("cyberagent/open-calm-3b") inputs = tokenizer("AIによって私達の暮らしは、", return_tensors="pt").to(model.device) with torch.no_grad(): tokens = model.generate( **inputs, max_new_tokens=64, do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.05, pad_token_id=tokenizer.pad_token_id, ) output = tokenizer.decode(tokens[0], skip_special_tokens=True) print(output)
Model | Params | Layers | Dim | Heads | Dev ppl |
---|---|---|---|---|---|
1232321 | 160M | 12 | 768 | 12 | 19.7 |
1233321 | 400M | 24 | 1024 | 16 | 13.8 |
1234321 | 830M | 24 | 1536 | 16 | 11.3 |
1235321 | 1.4B | 24 | 2048 | 16 | 10.3 |
1236321 | 2.7B | 32 | 2560 | 32 | 9.7 |
1237321 | 6.8B | 32 | 4096 | 32 | 8.2 |
@software{gpt-neox-library, title = {{GPT-NeoX: Large Scale Autoregressive Language Modeling in PyTorch}}, author = {Andonian, Alex and Anthony, Quentin and Biderman, Stella and Black, Sid and Gali, Preetham and Gao, Leo and Hallahan, Eric and Levy-Kramer, Josh and Leahy, Connor and Nestler, Lucas and Parker, Kip and Pieler, Michael and Purohit, Shivanshu and Songz, Tri and Phil, Wang and Weinbach, Samuel}, url = {https://www.github.com/eleutherai/gpt-neox}, doi = {10.5281/zenodo.5879544}, month = {8}, year = {2021}, version = {0.0.1}, }