MCPcopy Create free account

hub / github.com/QwenLM/Qwen3 / functions

Functions46 in github.com/QwenLM/Qwen3

⨍ Functions 46◇ Types & classes 4
↓ 3 callersFunction_clear_screen
()
examples/demo/cli_demo.py:113
↓ 3 callersFunctionget_content
( query, base_url, model_name, temperature, top_p, max_tokens, top_k, presence_penalty )
eval/generate_api_answers/utils_vllm.py:20
↓ 2 callersFunction_gc
()
examples/demo/cli_demo.py:105
↓ 2 callersMethod_reprs
(self, o)
examples/speed-benchmark/speed_benchmark_vllm.py:70
↓ 2 callersFunctioncreate_key
* Create a key for a tab element. * @param {HTMLElement} el - The tab element. * @returns {[string, string, string] | null} - The key. *
docs/source/_static/design-tabs.js:18
↓ 2 callersMethodcreate_query
(self, length: int, limited_size: int = 96)
examples/speed-benchmark/speed_benchmark_vllm.py:73
↓ 2 callersMethodrun_infer
(self, query: str)
examples/speed-benchmark/speed_benchmark_vllm.py:91
↓ 1 callersFunction_chat_stream
(model, tokenizer, query, history)
examples/demo/cli_demo.py:143
↓ 1 callersFunction_chat_stream
(model, tokenizer, query, history)
examples/demo/web_demo.py:76
↓ 1 callersFunction_gc
()
examples/demo/web_demo.py:102
↓ 1 callersFunction_get_args
()
examples/demo/web_demo.py:18
↓ 1 callersFunction_get_input
()
examples/demo/cli_demo.py:129
↓ 1 callersFunction_launch_demo
(args, model, tokenizer)
examples/demo/web_demo.py:110
↓ 1 callersFunction_load_model_tokenizer
(args)
examples/demo/cli_demo.py:83
↓ 1 callersFunction_load_model_tokenizer
(args)
examples/demo/web_demo.py:54
↓ 1 callersFunction_print_history
(history)
examples/demo/cli_demo.py:120
↓ 1 callersFunction_setup_readline
()
examples/demo/cli_demo.py:60
↓ 1 callersMethodcollect_statistics
(model_id_or_path, data, out_length, in_length, tp_size)
examples/speed-benchmark/speed_benchmark_vllm.py:154
↓ 1 callersFunctioncount_completed_samples
(output_file)
eval/generate_api_answers/infer_multithread.py:16
↓ 1 callersFunctionget_after_think
(text)
eval/eval/eval.py:12
↓ 1 callersFunctionmain
()
eval/eval/eval.py:20
↓ 1 callersFunctionmain
()
eval/generate_api_answers/infer_multithread.py:67
↓ 1 callersFunctionmain
()
examples/speed-benchmark/speed_benchmark_vllm.py:187
↓ 1 callersFunctionmain
()
examples/speed-benchmark/speed_benchmark_transformers.py:135
↓ 1 callersFunctionmain
()
examples/demo/cli_demo.py:169
↓ 1 callersFunctionmain
()
examples/demo/web_demo.py:197
↓ 1 callersFunctionparse_model_output
(output)
eval/eval/arc_agi_1.py:6
↓ 1 callersFunctionpredict
(_query, _chatbot, _task_history)
examples/demo/web_demo.py:111
↓ 1 callersMethodprint_table
(results)
examples/speed-benchmark/speed_benchmark_vllm.py:172
↓ 1 callersMethodrun
(self)
examples/speed-benchmark/speed_benchmark_vllm.py:101
↓ 1 callersMethodrun
(self, context_length: int, generate_length: int)
examples/speed-benchmark/speed_benchmark_transformers.py:59
↓ 1 callersFunctionsave_cache
(jobs, cache_path)
eval/eval/arc_agi_1.py:56
↓ 1 callersMethodsave_result
(data: dict, out_file: str)
examples/speed-benchmark/speed_benchmark_vllm.py:177
↓ 1 callersMethodsave_result
(data: dict, out_file: str)
examples/speed-benchmark/speed_benchmark_transformers.py:125
↓ 1 callersFunctionsolution_score
(predicted, ground_truth)
eval/eval/arc_agi_1.py:30
Method__init__
(self, experiment_config: dict, sampling_params: SamplingParams)
examples/speed-benchmark/speed_benchmark_vllm.py:38
Method__init__
Speed benchmark for transformers(pt) inference. Args: model_id_or_path: The model id on ModelScope or HuggingFace hub, o
examples/speed-benchmark/speed_benchmark_transformers.py:30
Function_completer
(text, state)
examples/demo/cli_demo.py:68
Methodadd_line
(self, line: str, source: str, *lineno: int)
docs/source/conf.py:112
Functioncompute_scores_arc_agi_1
(jobs, cache_path)
eval/eval/arc_agi_1.py:36
FunctiononSDLabelClick
* Activate other tabs with the same sync id. * * @this {HTMLElement} - The element that was clicked.
docs/source/_static/design-tabs.js:89
Functionprocess_item
( item, output_file, base_url, model_name, temperature, top_p, max_tokens, top
eval/generate_api_answers/infer_multithread.py:31
Functionready
* Initialize the tab selection. *
docs/source/_static/design-tabs.js:29
Functionregenerate
(_chatbot, _task_history)
examples/demo/web_demo.py:127
Functionreset_state
(_chatbot, _task_history)
examples/demo/web_demo.py:138
Functionreset_user_input
()
examples/demo/web_demo.py:135