MCPcopy Create free account

hub / github.com/allenai/OLMo / functions

Functions3,821 in github.com/allenai/OLMo

⨍ Functions 3,821◇ Types & classes 799↳ Endpoints 9
↓ 2 callersFunctionmain
(cfg: TrainConfig)
scripts/train.py:52
↓ 2 callersFunctionmake_metric
()
olmo/eval/__init__.py:87
↓ 2 callersFunctionmake_model
(flash_attn: bool)
tests/model_test.py:228
↓ 2 callersFunctionmake_quant
( module, names, bits, group_size, name="", use_triton: bool = False, disable_exll
inference/compression/dependencies/AutoGPTQ/auto_gptq/modeling/_utils.py:52
↓ 2 callersFunctionmetric_max_over_ground_truths
Compute max metric between prediction and each ground truth.
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:85
↓ 2 callersFunctionmetric_max_over_ground_truths
Compute max metric between prediction and each ground truth.
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:85
↓ 2 callersMethodmodel_forward
( self, batch: Dict[str, Any], loss_reduction: str = "mean", compute_z_loss: bool = False )
olmo/train.py:720
↓ 2 callersFunctionmove_to_device
(o: T, device: torch.device)
olmo/torch_util.py:68
↓ 2 callersFunctionnormalize_answer
Taken from the official evaluation script for v1.1 of the SQuAD dataset. Lower text and remove punctuation, articles and extra whitespace.
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/qasper.py:43
↓ 2 callersFunctionnormalize_answer
Taken from the official evaluation script for v1.1 of the SQuAD dataset. Lower text and remove punctuation, articles and extra whitespace.
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/qasper.py:43
↓ 2 callersFunctionoa_completion
Query OpenAI API for completion. Retry with back-off until they respond
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:39
↓ 2 callersFunctionoa_completion
Query OpenAI API for completion. Retry with back-off until they respond
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:39
↓ 2 callersMethodoffline_data_path
(self, base_dir: str)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/tasks/efficiency_benchmark.py:50
↓ 2 callersMethodoffline_data_path
(self, base_dir: str)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/tasks/efficiency_benchmark.py:50
↓ 2 callersFunctionpack_in
(n, m, nb, mb)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:112
↓ 2 callersFunctionpack_out
(n, t, nb, tb)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:135
↓ 2 callersFunctionpack_qw
(m, t, mb, tb, tb1, bits=4, cutoff=-1)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:158
↓ 2 callersFunctionpack_qw_module
(bits)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:1468
↓ 2 callersFunctionparse_run_path
For convenience, we allow run paths as well as URLs.
scripts/compare_wandb_configs.py:27
↓ 2 callersMethodpartial_context
(cls, doc, option)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/winogrande.py:65
↓ 2 callersMethodpartial_context
(cls, doc, option)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/wsc273.py:105
↓ 2 callersMethodpartial_context
(cls, doc, option)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/winogrande.py:65
↓ 2 callersMethodpartial_context
(cls, doc, option)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/wsc273.py:105
↓ 2 callersMethodpartial_target
(cls, doc)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/winogrande.py:75
↓ 2 callersMethodpartial_target
(cls, doc)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/wsc273.py:114
↓ 2 callersMethodpartial_target
(cls, doc)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/winogrande.py:75
↓ 2 callersMethodpartial_target
(cls, doc)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/wsc273.py:114
↓ 2 callersFunctionpostprocess_generation_ids
( input_ids: LongTensor, output_ids: LongTensor, num_return_sequences: int, tokenizer: Optiona
inference/compression/dependencies/AutoGPTQ/auto_gptq/eval_tasks/_utils/generation_utils.py:7
↓ 2 callersMethodpredict
(self, inputs)
inference/efficiency/run_efficiency_benchmark.py:51
↓ 2 callersMethodpredict
( # type: ignore self, *, input_batches: List[List[Dict[str, Any]]], max_batch_size: int )
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/stdio_wrapper.py:81
↓ 2 callersMethodpredict
( # type: ignore self, *, input_batches: List[List[Dict[str, Any]]], max_batch_size: int )
inference/efficiency/dependencies/previous_version/efficiency_benchmark/stdio_wrapper.py:81
↓ 2 callersMethodpreprocess
(cls, text)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/hellaswag.py:62
↓ 2 callersMethodpreprocess
(cls, text)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/hellaswag.py:62
↓ 2 callersMethodpreprocess
(cls, string: str)
olmo/eval/downstream.py:1094
↓ 2 callersFunctionprint_keys_with_differences
(left_config, right_config)
scripts/compare_wandb_configs.py:41
↓ 2 callersFunctionprint_line
(line: str)
inference/efficiency/dependencies/efficiency-pentathlon/eb_gantry/util.py:74
↓ 2 callersFunctionprint_parameters
(bits, n, m, t, nb, mb, tb, mu, nu, tu, unroll, p, gs=-1)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:94
↓ 2 callersMethodprune_configs
(self, kwargs)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/triton_utils/custom_autotune.py:109
↓ 2 callersFunctionquantize
(x, scale, zero, maxq)
inference/compression/dependencies/AutoGPTQ/auto_gptq/quantization/quantizer.py:9
↓ 2 callersMethodready
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/quantization/quantizer.py:127
↓ 2 callersMethodremove_boxed
(self, s)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/hendrycks_math.py:104
↓ 2 callersMethodremove_boxed
(self, s)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/hendrycks_math.py:104
↓ 2 callersMethodremove_ephemeral_checkpoint
(self, idx: int = 0)
olmo/train.py:535
↓ 2 callersMethodreset
( self, )
olmo/eval/downstream.py:36
↓ 2 callersMethodreset_metrics
(self)
olmo/eval/evaluator.py:22
↓ 2 callersMethodreshuffle
(self, epoch: int)
olmo/data/iterable_dataset.py:121
↓ 2 callersMethodrestore_checkpoint
( self, load_path: PathOrStr, dist_model: nn.Module, optim: Optimizer,
olmo/checkpoint.py:680
↓ 2 callersMethodrun
(self, generation_config: Optional[GenerationConfig] = None)
inference/compression/dependencies/AutoGPTQ/auto_gptq/eval_tasks/sequence_classification_task.py:91
↓ 2 callersMethodrun
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/eval_tasks/language_modeling_task.py:43
↓ 2 callersMethodrun
(self, generation_config: Optional[GenerationConfig] = None)
inference/compression/dependencies/AutoGPTQ/auto_gptq/eval_tasks/text_summarization_task.py:63
↓ 2 callersMethodsample_beams
( self, log_probs: torch.Tensor, beam_size: int, state: StateType )
olmo/beam_search.py:94
↓ 2 callersMethodsample_nodes
( self, log_probs: torch.Tensor, per_node_beam_size: int, state: StateType )
olmo/beam_search.py:238
↓ 2 callersFunctionsample_stddev
(arr)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:19
↓ 2 callersFunctionsample_stddev
(arr)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:19
↓ 2 callersMethodsave
(self, obj, save_persistent_id=True)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/tango_utils/det_hash.py:115
↓ 2 callersMethodsave_checkpoint
( self, dir: PathOrStr, dist_model: nn.Module, optim: Optimizer, train
olmo/checkpoint.py:619
↓ 2 callersFunctionshould_checkpoint_block
(strategy: Optional[ActivationCheckpointingStrategy], block_idx: int)
olmo/model.py:92
↓ 2 callersFunctionshow_oe_eval_task
(config_file, dir, num_examples, sub_dir=None)
scripts/list_evals_from_oe_eval.py:14
↓ 2 callersFunctionsimple_dispatch_model
(model, device_map)
inference/compression/dependencies/AutoGPTQ/auto_gptq/modeling/_utils.py:165
↓ 2 callersMethodstart
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/efficiency/profiler.py:98
↓ 2 callersMethodstart
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/efficiency/profiler.py:98
↓ 2 callersFunctionstderr_console
()
inference/efficiency/dependencies/efficiency-pentathlon/eb_gantry/util.py:43
↓ 2 callersMethodstrip_string
(self, string)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/hendrycks_math.py:218
↓ 2 callersMethodstrip_string
(self, string)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/hendrycks_math.py:218
↓ 2 callersFunctionsynchronize_value
(value: V, device: torch.device)
olmo/torch_util.py:129
↓ 2 callersMethodsystem_metrics
(self)
olmo/train.py:944
↓ 2 callersFunctiont5_prompt_conversion
( *, task_name: str, label_field: str = "label", label_map: Dict[int, str], use_fields: Op
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/tasks/t5.py:6
↓ 2 callersFunctiont5_prompt_conversion
( *, task_name: str, label_field: str = "label", label_map: Dict[int, str], use_fields: Op
inference/efficiency/dependencies/previous_version/efficiency_benchmark/tasks/t5.py:6
↓ 2 callersFunctiontextsynth_completion
Query TextSynth API for completion. Retry with back-off until they respond.
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:25
↓ 2 callersFunctiontextsynth_completion
Query TextSynth API for completion. Retry with back-off until they respond.
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:25
↓ 2 callersMethodtok_encode
(self, string: str)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:110
↓ 2 callersMethodtok_encode
(self, string: str)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:110
↓ 2 callersFunctiontranspose_quant_matmul_248
(input, qweight, scales, qzeros, g_idx, bits, maxq)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/triton_utils/kernels.py:317
↓ 2 callersMethodtriton_llama_mlp
(self, x)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/fused_llama_mlp.py:221
↓ 2 callersMethodtry_close_serial_port
(ser: Serial)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/efficiency/power_monitor.py:36
↓ 2 callersMethodtry_close_serial_port
(ser: Serial)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/efficiency/power_monitor.py:36
↓ 2 callersMethodtry_open_serial_port
(serial_port: str = "/dev/ttyUSB0", baud_rate: int = 115200)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/efficiency/power_monitor.py:29
↓ 2 callersMethodtry_open_serial_port
(serial_port: str = "/dev/ttyUSB0", baud_rate: int = 115200)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/efficiency/power_monitor.py:29
↓ 2 callersFunctionunpack_zeros
(bits)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:1285
↓ 2 callersFunctionunquantize_sim
(p)
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/generate.py:1433
↓ 2 callersMethodupdate_legacy_settings
Update the legacy config settings whose schemas have undergone backwards-incompatible changes.
olmo/config.py:109
↓ 2 callersMethodupdate_metrics
( self, batch: Dict[str, Any], ce_loss: torch.Tensor, logits: torch.Tensor,
olmo/eval/evaluator.py:67
↓ 2 callersMethodupload
Uploads the content from the directory or file at the local FS source to the path.
scripts/storage_cleaner.py:94
↓ 2 callersFunctionweighted_mean
(items)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:98
↓ 2 callersFunctionweighted_mean
(items)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:98
↓ 2 callersFunctionword_ngrams
Splits a string into ngram words
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/decontamination/janitor.py:39
↓ 2 callersFunctionword_ngrams
Splits a string into ngram words
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/decontamination/janitor.py:39
↓ 2 callersMethodwrap
(cls, scheduler: Scheduler, warmup_start: int, warmup_end: int)
olmo/optim.py:760
↓ 2 callersFunctionwrite_config
(checkpoint_dir: str)
hf_olmo/convert_olmo_to_hf.py:51
↓ 2 callersFunctionwrite_model
(checkpoint_dir: str, ignore_olmo_compatibility: bool = False)
hf_olmo/convert_olmo_to_hf.py:66
↓ 2 callersFunctionwrite_to_gsheet
(gsheet: str, rows: List[Dict], sheet_title: str = "Sheet1")
evaluation/steps/run_catwalk.py:353
↓ 2 callersFunctionwrite_tokenizer
(checkpoint_dir: str)
hf_olmo/convert_olmo_to_hf.py:88
↓ 1 callersMethod__contains__
(self, item)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/tango_utils/sequences.py:236
↓ 1 callersMethod__contains__
(self, item)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/tango_utils/sequences.py:236
↓ 1 callersMethod__getstate__
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/tasks/eleuther.py:56
↓ 1 callersMethod__getstate__
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/tasks/eleuther.py:56
↓ 1 callersMethod__init__
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/metrics/accuracy.py:16
↓ 1 callersMethod__init__
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/hendrycks_test.py:98
↓ 1 callersMethod__init__
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/translation.py:88
↓ 1 callersMethod__init__
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/metrics/accuracy.py:16
← previousnext →401–500 of 3,821, ranked by callers