54 lines
4.5 KiB
Python
54 lines
4.5 KiB
Python
|
import pytest
|
||
|
|
import torch
|
||
|
|
|
||
|
|
import vllm
|
||
|
|
from vllm.lora.request import LoRARequest
|
||
|
|
|
||
|
|
MODEL_PATH = "mistralai/Mixtral-8x7B-Instruct-v0.1"
|
||
|
|
|
||
|
|
|
||
|
|
def do_sample(llm, lora_path: str, lora_id: int):
|
||
|
|
prompts = [
|
||
|
|
"[system] Given a target sentence construct the underlying meaning representation\nof the input sentence as a single function with attributes and attribute\nvalues. This function should describe the target string accurately and the\nfunction must be one of the following ['inform', 'request', 'give_opinion',\n'confirm', 'verify_attribute', 'suggest', 'request_explanation',\n'recommend', 'request_attribute'].\n\nThe attributes must be one of the following:\n['name', 'exp_release_date', 'release_year', 'developer', 'esrb', 'rating',\n'genres', 'player_perspective', 'has_multiplayer', 'platforms',\n'available_on_steam', 'has_linux_release', 'has_mac_release', 'specifier'] [/system] [user] Here is the target sentence:\nSpellForce 3 is a pretty bad game. The developer Grimlore Games is clearly a bunch of no-talent hacks, and 2017 was a terrible year for games anyway. [/user] [assistant]",
|
||
|
|
"[system] Given a target sentence construct the underlying meaning representation\nof the input sentence as a single function with attributes and attribute\nvalues. This function should describe the target string accurately and the\nfunction must be one of the following ['inform', 'request', 'give_opinion',\n'confirm', 'verify_attribute', 'suggest', 'request_explanation',\n'recommend', 'request_attribute'].\n\nThe attributes must be one of the following:\n['name', 'exp_release_date', 'release_year', 'developer', 'esrb', 'rating',\n'genres', 'player_perspective', 'has_multiplayer', 'platforms',\n'available_on_steam', 'has_linux_release', 'has_mac_release', 'specifier'] [/system] [user] Here is the target sentence:\nI wanted to like Grimlore Games' 2017 entry, but in SpellForce 3 they just didn't get anything right. [/user] [assistant]",
|
||
|
|
"[system] Given a target sentence construct the underlying meaning representation\nof the input sentence as a single function with attributes and attribute\nvalues. This function should describe the target string accurately and the\nfunction must be one of the following ['inform', 'request', 'give_opinion',\n'confirm', 'verify_attribute', 'suggest', 'request_explanation',\n'recommend', 'request_attribute'].\n\nThe attributes must be one of the following:\n['name', 'exp_release_date', 'release_year', 'developer', 'esrb', 'rating',\n'genres', 'player_perspective', 'has_multiplayer', 'platforms',\n'available_on_steam', 'has_linux_release', 'has_mac_release', 'specifier'] [/system] [user] Here is the target sentence:\nBioShock is a good role-playing, action-adventure, shooter that released for PlayStation, Xbox, and PC in 2007. It is available on Steam, and it has a Mac release but not a Linux release. [/user] [assistant]",
|
||
|
|
]
|
||
|
|
sampling_params = vllm.SamplingParams(temperature=0, max_tokens=256)
|
||
|
|
outputs = llm.generate(
|
||
|
|
prompts,
|
||
|
|
sampling_params,
|
||
|
|
lora_request=LoRARequest(str(lora_id), lora_id, lora_path)
|
||
|
|
if lora_id else None)
|
||
|
|
# Print the outputs.
|
||
|
|
generated_texts = []
|
||
|
|
for output in outputs:
|
||
|
|
prompt = output.prompt
|
||
|
|
generated_text = output.outputs[0].text.strip()
|
||
|
|
generated_texts.append(generated_text)
|
||
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
||
|
|
return generated_texts
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize("tp_size", [4])
|
||
|
|
def test_mixtral_lora(mixtral_lora_files, tp_size):
|
||
|
|
if torch.cuda.device_count() < tp_size:
|
||
|
|
pytest.skip(f"Not enough GPUs for tensor parallelism {tp_size}")
|
||
|
|
|
||
|
|
llm = vllm.LLM(MODEL_PATH,
|
||
|
|
enable_lora=True,
|
||
|
|
max_num_seqs=16,
|
||
|
|
max_loras=4,
|
||
|
|
tensor_parallel_size=tp_size,
|
||
|
|
worker_use_ray=True)
|
||
|
|
|
||
|
|
expected_lora_output = [
|
||
|
|
"give_opinion(name[SpellForce 3], release_year[2017], developer[Grimlore Games], rating[poor])",
|
||
|
|
"give_opinion(name[SpellForce 3], release_year[2017], developer[Grimlore Games], rating[poor])",
|
||
|
|
"inform(name[BioShock], release_year[2007], rating[good], genres[action-adventure, role-playing, shooter], platforms[PlayStation, Xbox, PC], available_on_steam[yes], has_linux_release[no], has_mac_release[yes])",
|
||
|
|
]
|
||
|
|
|
||
|
|
assert do_sample(llm, mixtral_lora_files,
|
||
|
|
lora_id=1) == expected_lora_output
|
||
|
|
assert do_sample(llm, mixtral_lora_files,
|
||
|
|
lora_id=2) == expected_lora_output
|