|
--- |
|
license: apache-2.0 |
|
language: |
|
- ja |
|
- en |
|
--- |
|
## Description |
|
This model is a 10.2 billion parameter model that combines two sets of 24 layers each from [CALM2-7B](https://huggingface.co/cyberagent/calm2-7b) using slerp-merge. |
|
|
|
## Note |
|
This model is experimental and may not achieve expected performance without additional tuning. |
|
|
|
## Tutorial |
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import torch |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("sudy-super/baku-10b") |
|
model = AutoModelForCausalLM.from_pretrained("sudy-super/baku-10b", device_map="auto", torch_dtype=torch.bfloat16) |
|
|
|
prompt = "大規模言語モデルとは、" |
|
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") |
|
with torch.no_grad(): |
|
output_ids = model.generate( |
|
token_ids.to(model.device), |
|
max_new_tokens=100, |
|
do_sample=True, |
|
temperature=0.8, |
|
pad_token_id=tokenizer.pad_token_id, |
|
bos_token_id=tokenizer.bos_token_id, |
|
eos_token_id=tokenizer.eos_token_id |
|
) |
|
result = tokenizer.decode(output_ids.tolist()[0]) |
|
|
|
print(result) |
|
``` |
