File size: 1,131 Bytes
6dff36a 45e7094 a8b9616 45e7094 a8b9616 c5cd957 2996520 a8b9616 8610593 a8b9616 8610593 a8b9616 6dff36a a8b9616 c5cd957 a8b9616 6dff36a a8b9616 6dff36a c5cd957 a8b9616 6dff36a c5cd957 |
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 |
---
language:
- en
---
## Ars model
This model was trained on stanford alpaca dataset
## To Run:
from peft import PeftModel
from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig
tokenizer = LLaMATokenizer.from_pretrained("decapoda-research/llama-7b-hf")
model = LLaMAForCausalLM.from_pretrained(
"decapoda-research/llama-7b-hf",
load_in_8bit=True,
device_map="auto",
)\
model = PeftModel.from_pretrained(model, "patulya/ars")
PROMPT = """Below is an instruction that describes a task. Write a response that appropriately completes the request.
\### Instruction:
{your_instruction}
\### Response:"""
inputs = tokenizer(
PROMPT,
return_tensors="pt",
)
input_ids = inputs["input_ids"].cuda()
generation_config = GenerationConfig(\
temperature=0.6,\
top_p=0.95,\
repetition_penalty=1.15,\
)
print("Generating...")
generation_output = model.generate(\
input_ids=input_ids,\
generation_config=generation_config,\
return_dict_in_generate=True,\
output_scores=True,\
max_new_tokens=128,\
)
for s in generation_output.sequences: print(tokenizer.decode(s)) |