mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
7505b3cadf
* add TheoremQA with 5-shot * add huggingface_above_v4_33 classes * use num_worker partitioner in cli * update theoremqa * update TheoremQA * add TheoremQA * rename theoremqa -> TheoremQA * update TheoremQA output path * rewrite many model configs * update huggingface * further update * refine configs * update configs * update configs * add configs/eval_llama3_instruct.py * add summarizer multi faceted * update bbh datasets * update configs/models/hf_llama/lmdeploy_llama3_8b_instruct.py * rename class * update readme * update hf above v4.33
25 lines
815 B
Python
25 lines
815 B
Python
from opencompass.models import TurboMindModel
|
|
|
|
_meta_template = dict(
|
|
round=[
|
|
dict(role="HUMAN", begin='<|begin_of_text|>user<|end_header_id|>\n\n', end='<|eot_id|>'),
|
|
dict(role="BOT", begin='<|begin_of_text|>assistant<|end_header_id|>\n\n', end='<|eot_id|>', generate=True),
|
|
],
|
|
)
|
|
|
|
models = [
|
|
dict(
|
|
type=TurboMindModel,
|
|
abbr='llama-3-70b-instruct-lmdeploy',
|
|
path='meta-llama/Meta-Llama-3-70B-Instruct',
|
|
engine_config=dict(session_len=4096, max_batch_size=16, tp=4),
|
|
gen_config=dict(top_k=1, temperature=1, top_p=0.9, max_new_tokens=1024, stop_words=[128001, 128009]),
|
|
max_out_len=1024,
|
|
max_seq_len=4096,
|
|
batch_size=16,
|
|
concurrency=16,
|
|
meta_template=_meta_template,
|
|
run_cfg=dict(num_gpus=4),
|
|
)
|
|
]
|