File size: 1,599 Bytes
a858739 e2c44ff c59532d e2c44ff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
---
license: apache-2.0
---
## usage :
```python
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
# set HF_TOKEN in terminal as export HF_TOKEN=hf_***
auth_token = os.environ.get("HF_TOKEN", True)
model_name = "Writer/camel-5b"
tokenizer = AutoTokenizer.from_pretrained(
model_name, use_auth_token=auth_token
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype=torch.float16,
use_auth_token=auth_token,
)
instruction = "Describe a futuristic device that revolutionizes space travel."
PROMPT_DICT = {
"prompt_input": (
"Below is an instruction that describes a task, paired with an input that provides further context. "
"Write a response that appropriately completes the request\n\n"
"### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
),
"prompt_no_input": (
"Below is an instruction that describes a task. "
"Write a response that appropriately completes the request.\n\n"
"### Instruction:\n{instruction}\n\n### Response:"
),
}
text = (
PROMPT_DICT["prompt_no_input"].format(instruction=instruction)
if not input
else PROMPT_DICT["prompt_input"].format(instruction=instruction, input=input)
)
model_inputs = tokenizer(text, return_tensors="pt").to("cuda")
output_ids = model.generate(
**model_inputs,
max_length=100,
)
output_text = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]
clean_output = output_text.split("### Response:")[1].strip()
print(clean_output)
```
|