MCPcopy Create free account

hub / github.com/CoopReason/TESSY / functions

Functions39 in github.com/CoopReason/TESSY

⨍ Functions 39◇ Types & classes 1
↓ 3 callersFunctiongenerate_and_update_model_states_async
( classifier_tokenizer, classifier_model, tokenizer_for_llm, current_model_name, inpu
run_tessy.py:221
↓ 2 callersFunctionappend_jsonl
(path: str, data: dict)
Boundary_Predictor/generate_responses.py:35
↓ 2 callersFunctionappend_jsonl
(path: str, data: dict)
Boundary_Predictor/annotator.py:39
↓ 2 callersFunctionbuild_prompt
(tokenizer, prompt, enable_think, name)
run_tessy.py:25
↓ 2 callersFunctiondetect_consecutive_repetition_hash
(text, min_repeat_len=3, min_repeat_times=8, base=257, mod=10 ** 9 + 7)
utils.py:49
↓ 2 callersFunctionget_hashes_and_lines
(raw_line)
utils.py:93
↓ 2 callersFunctionget_hashes_and_lines
(raw_line)
Boundary_Predictor/generate_responses.py:12
↓ 2 callersFunctionparse_and_locate_spans
Parse model output (should be JSON list[str]) and find the (start, end) index of each span in the original text. Returns: [
Boundary_Predictor/annotator.py:130
↓ 1 callersFunctionappend_jsonl
(path: str, data: dict)
utils.py:121
↓ 1 callersFunctionasync_main
(args)
run_tessy.py:361
↓ 1 callersFunctionbuild_prompt
Construct prompt: Request the model to extract all transitional, tonal, and filler phrases without substantial reasoning content, return a JS
Boundary_Predictor/annotator.py:86
↓ 1 callersFunctioncall_vllm_api_async
(session: aiohttp.ClientSession, api_url: str, model_name: str, prompt: str, max_tokens: int, temperature: flo
run_tessy.py:51
↓ 1 callersFunctionclassify_next_token_decision
(batch_cur_texts, batch_generated_texts, current_model_name, classifier_toke
run_tessy.py:104
↓ 1 callersFunctionconstruct_dataset
(path, data_size)
Boundary_Predictor/annotator.py:52
↓ 1 callersFunctionevaluate
(model, dataloader, device)
Boundary_Predictor/train_predictor.py:271
↓ 1 callersFunctiongenerate_response
(args)
Boundary_Predictor/generate_responses.py:54
↓ 1 callersFunctiongenerate_response
(args)
Boundary_Predictor/annotator.py:174
↓ 1 callersFunctionis_symbolic
(text)
utils.py:45
↓ 1 callersFunctionload_dataset
(file_path, tokenizer, val_ratio=0.05, seed=42, sample_limit=None)
Boundary_Predictor/train_predictor.py:219
↓ 1 callersFunctionload_processed_ids
(path_save: str)
utils.py:127
↓ 1 callersFunctionload_processed_ids
(path_save: str)
Boundary_Predictor/generate_responses.py:40
↓ 1 callersFunctionload_processed_ids
(path_save: str)
Boundary_Predictor/annotator.py:44
↓ 1 callersFunctionmain
()
Boundary_Predictor/train_predictor.py:309
↓ 1 callersFunctionpost_process_text
(text, enable_think)
utils.py:109
↓ 1 callersFunctionpredict_dataset
(model, tokenizer, dataloader, device, output_file=None)
Boundary_Predictor/train_predictor.py:115
↓ 1 callersFunctionread_jsonl
(path)
utils.py:97
↓ 1 callersFunctionread_jsonl
(path)
Boundary_Predictor/generate_responses.py:16
↓ 1 callersFunctionread_jsonl
(path)
Boundary_Predictor/annotator.py:19
↓ 1 callersFunctiontrain_one_epoch
(model, dataloader, optimizer, device, log_interval=10)
Boundary_Predictor/train_predictor.py:243
Method__getitem__
(self, idx)
Boundary_Predictor/train_predictor.py:23
Method__init__
(self, samples, tokenizer, max_length=512)
Boundary_Predictor/train_predictor.py:15
Method__len__
(self)
Boundary_Predictor/train_predictor.py:20
Function_strip_block
(m)
utils.py:30
Functioncollate_fn
(batch)
Boundary_Predictor/train_predictor.py:93
Functionget_hashes_and_lines
(raw_line)
Boundary_Predictor/annotator.py:15
Functionjudge_think_end_correct
(response)
utils.py:7
Functionremove_triple_backticks
(text: str)
utils.py:12
Functionsave_jsonl
(data, filename)
Boundary_Predictor/generate_responses.py:29
Functionsave_jsonl
(data, filename)
Boundary_Predictor/annotator.py:32