-
Notifications
You must be signed in to change notification settings - Fork 416
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #326 from Anhforth/merge_aquila
Merge aquila
- Loading branch information
Showing
24 changed files
with
691 additions
and
231 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,109 @@ | ||
| import os | ||
| import torch | ||
| from flagai.auto_model.auto_loader import AutoLoader | ||
| from flagai.model.predictor.predictor import Predictor | ||
| from flagai.model.predictor.aquila import aquila_generate | ||
| from flagai.data.tokenizer import Tokenizer | ||
| import bminf | ||
|
|
||
| state_dict = "/data2/yzd/checkpoints/converted_models_ldwang" | ||
| model_name = 'aquilachat-7b' | ||
|
|
||
| loader = AutoLoader( | ||
| "lm", | ||
| model_dir=state_dict, | ||
| model_name=model_name, | ||
| use_cache=True) | ||
| model = loader.get_model() | ||
| tokenizer = loader.get_tokenizer() | ||
| cache_dir = os.path.join(state_dict, model_name) | ||
|
|
||
| model.eval() | ||
| model.half() | ||
|
|
||
| with torch.cuda.device(0): | ||
| model = bminf.wrapper(model, quantization=False, memory_limit=2 << 30) | ||
|
|
||
| predictor = Predictor(model, tokenizer) | ||
|
|
||
| texts = [ | ||
| "北京为什么是中国的首都？", | ||
| "1+1=", | ||
| "为什么湘菜那么甜？", | ||
| "东三省和海南岛的区别？", | ||
| ] | ||
| ## | ||
| def pack_obj(text): | ||
| obj = dict() | ||
| obj['id'] = 'demo' | ||
|
|
||
| obj['conversations'] = [] | ||
| human = dict() | ||
| human['from'] = 'human' | ||
| human['value'] = text | ||
| obj['conversations'].append(human) | ||
| # dummy bot | ||
| bot = dict() | ||
| bot['from'] = 'gpt' | ||
| bot['value'] = '' | ||
| obj['conversations'].append(bot) | ||
|
|
||
| obj['instruction'] = '' | ||
|
|
||
| return obj | ||
|
|
||
| def delete_last_bot_end_singal(convo_obj): | ||
| conversations = convo_obj['conversations'] | ||
| assert len(conversations) > 0 and len(conversations) % 2 == 0 | ||
| assert conversations[0]['from'] == 'human' | ||
|
|
||
| last_bot = conversations[len(conversations)-1] | ||
| assert last_bot['from'] == 'gpt' | ||
|
|
||
| ## from _add_speaker_and_signal | ||
| END_SIGNAL = "\n" | ||
| len_end_singal = len(END_SIGNAL) | ||
| len_last_bot_value = len(last_bot['value']) | ||
| last_bot['value'] = last_bot['value'][:len_last_bot_value-len_end_singal] | ||
| return | ||
|
|
||
| def convo_tokenize(convo_obj, tokenizer): | ||
| chat_desc = convo_obj['chat_desc'] | ||
| instruction = convo_obj['instruction'] | ||
| conversations = convo_obj['conversations'] | ||
|
|
||
| # chat_desc | ||
| example = tokenizer.encode_plus(f"{chat_desc}", None, max_length=None)['input_ids'] | ||
| EOS_TOKEN = example[-1] | ||
| example = example[:-1] # remove eos | ||
| # instruction | ||
| instruction = tokenizer.encode_plus(f"{instruction}", None, max_length=None)['input_ids'] | ||
| instruction = instruction[1:-1] # remove bos & eos | ||
| example += instruction | ||
|
|
||
| for conversation in conversations: | ||
| role = conversation['from'] | ||
| content = conversation['value'] | ||
| print(f"role {role}, raw content {content}") | ||
| content = tokenizer.encode_plus(f"{content}", None, max_length=None)['input_ids'] | ||
| content = content[1:-1] # remove bos & eos | ||
| print(f"role {role}, content {content}") | ||
| example += content | ||
| return example | ||
|
|
||
| for text in texts: | ||
| print('-'*80) | ||
| print(f"text is {text}") | ||
|
|
||
| from cyg_conversation import default_conversation | ||
|
|
||
| conv = default_conversation.copy() | ||
| conv.append_message(conv.roles[0], text) | ||
| conv.append_message(conv.roles[1], None) | ||
|
|
||
| tokens = tokenizer.encode_plus(f"{conv.get_prompt()}", None, max_length=None)['input_ids'] | ||
| tokens = tokens[1:-1] | ||
|
|
||
| with torch.no_grad(): | ||
| out = aquila_generate(tokenizer, model, [text], max_gen_len:=200, top_p=0.95, prompts_tokens=[tokens]) | ||
| print(f"pred is {out}") |
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file was deleted.
Oops, something went wrong.
Oops, something went wrong.