Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/allenai/OLMo
/ functions
Functions
3,821 in github.com/allenai/OLMo
⨍
Functions
3,821
◇
Types & classes
799
↳
Endpoints
9
Method
loglikelihood
(self, requests)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:89
Method
loglikelihood
(self, requests)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/base.py:177
Method
loglikelihood
(self, requests)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:89
Method
loglikelihood_rolling
(self, requests)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/base.py:192
Method
loglikelihood_rolling
(self, requests)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:107
Method
loglikelihood_rolling
(self, requests)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/dummy.py:31
Method
loglikelihood_rolling
(self, requests)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/base.py:192
Method
loglikelihood_rolling
(self, requests)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:107
Method
loglikelihood_rolling
(self, requests)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/dummy.py:31
Function
lorem_ipsum
()
conftest.py:87
Function
lorem_ipsum_docs
()
conftest.py:92
Function
make_data_block
A simple implementation of text generation oriented smart batching to maximize VRAM usage when evaluation :param samples: Dict[str, List[str]], s
inference/compression/dependencies/AutoGPTQ/auto_gptq/utils/data_utils.py:13
Function
make_disjoint_window
Takes output from get_rolling_token_windows and makes the context not overlap with the continuation
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/utils.py:116
Function
make_disjoint_window
Takes output from get_rolling_token_windows and makes the context not overlap with the continuation
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/utils.py:116
Function
make_table
Generate table of results.
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/evaluator.py:282
Function
make_table
Generate table of results.
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/evaluator.py:282
Method
manual_download_instructions
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/datasets/sat_analogies/sat_analogies.py:59
Method
manual_download_instructions
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/datasets/sat_analogies/sat_analogies.py:59
Method
massage_kwargs
(cls, kwargs: Dict[str, Any])
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/steps.py:102
Method
massage_kwargs
(cls, kwargs: Dict[str, Any])
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/steps.py:211
Method
massage_kwargs
(cls, kwargs: Dict[str, Any])
inference/efficiency/dependencies/previous_version/efficiency_benchmark/steps.py:98
Method
massage_kwargs
(cls, kwargs: Dict[str, Any])
inference/efficiency/dependencies/previous_version/efficiency_benchmark/steps.py:203
Function
matmul248_kernel_config_pruner
The main purpose of this function is to shrink BLOCK_SIZE_* when the corresponding dimension is smaller.
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/triton_utils/custom_autotune.py:153
Function
matthews_corrcoef
(items)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:32
Function
matthews_corrcoef
(items)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:32
Method
max_epochs
(self)
olmo/train.py:257
Method
max_gen_toks
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/base.py:138
Method
max_gen_toks
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/gpt2.py:88
Method
max_gen_toks
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:68
Method
max_gen_toks
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:97
Method
max_gen_toks
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/base.py:138
Method
max_gen_toks
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/gpt2.py:88
Method
max_gen_toks
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:68
Method
max_gen_toks
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:97
Method
max_length
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/base.py:133
Method
max_length
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/gpt2.py:80
Method
max_length
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:63
Method
max_length
(self)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:92
Method
max_length
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/base.py:133
Method
max_length
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/gpt2.py:80
Method
max_length
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/textsynth.py:63
Method
max_length
(self)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/models/gpt3.py:92
Method
max_seq_len
(self)
olmo/data/memmap_dataset.py:97
Method
max_steps
(self)
olmo/train.py:261
Method
max_tokens
(self)
olmo/train.py:281
Method
mc1
(lls)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/truthfulqa.py:126
Method
mc1
(lls)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/truthfulqa.py:126
Method
mc2
(lls)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/truthfulqa.py:130
Method
mc2
(lls)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/truthfulqa.py:130
Function
median
(arr)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:28
Function
median
(arr)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:28
Function
memoize
(user_function, /)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/task.py:43
Function
memoize
(user_function, /)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/task.py:43
Method
merge
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/utils/peft_utils.py:57
Method
merge_adapter
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/utils/peft_utils.py:168
Method
merge_adapter
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/utils/peft_utils.py:301
Method
merge_and_unload
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/utils/peft_utils.py:174
Method
merge_and_unload
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/utils/peft_utils.py:307
Function
model_config
()
conftest.py:44
Function
model_path
()
conftest.py:97
Function
module
(bits_list=[4, 2])
inference/compression/dependencies/AutoGPTQ/autogptq_extension/qigen/template.py:15
Method
new_step
(last_predictions: torch.Tensor, state: Dict[str, torch.Tensor], time_step: int)
olmo/beam_search.py:805
Function
nodecounts_cmd
(args: argparse.Namespace)
scripts/ladder.py:313
Method
normalize
(text)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/datasets/logiqa/logiqa.py:109
Method
normalize
(text)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/datasets/logiqa/logiqa.py:109
Method
num_attention_heads
(self)
hf_olmo/configuration_olmo.py:29
Method
num_bck_flops
(self)
olmo/model.py:1587
Method
num_fwd_flops
(self)
olmo/model.py:1569
Method
num_hidden_layers
(self)
hf_olmo/configuration_olmo.py:33
Method
offsets
(self)
olmo/data/memmap_dataset.py:102
Method
on_trace_ready
(p)
olmo/train.py:1145
Method
output_multiplier
(self)
olmo/model.py:334
Method
output_multiplier
(self)
olmo/model.py:351
Method
output_multiplier
(self)
olmo/model.py:357
Method
output_multiplier
(self)
olmo/model.py:367
Method
pack
(self, linear, scales, zeros, g_idx)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/qlinear/qlinear_cuda_old.py:98
Method
pack
(self, linear, scales, zeros, g_idx=None)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/qlinear/qlinear_triton.py:66
Method
pack
(self, linear, scales, zeros, g_idx=None)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/qlinear/qlinear_exllama.py:100
Method
pad_token
(self)
olmo/tokenizer.py:54
Function
partial_size
(s3_uri: str)
scripts/microanneal_config_maker.py:39
Function
partial_size
(s3_uri: str)
scripts/peteish7_config_maker.py:38
Function
pass_through_fn
(fn, *args, **kwargs)
olmo/util.py:796
Function
patched_get_worker_info
()
tests/data/iterable_dataset_test.py:89
Method
path_choose
(*paths)
olmo/config.py:80
Method
path_glob
(*paths)
olmo/config.py:70
Method
path_last_checkpoint
(path)
olmo/config.py:92
Function
perplexity
(items)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:94
Function
perplexity
(items)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:94
Method
persistent_id
(self, obj: Any)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/tango_utils/det_hash.py:120
Method
persistent_id
(self, obj: Any)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/tango_utils/det_hash.py:120
Function
pop_stddev
(arr)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/metrics.py:14
Function
pop_stddev
(arr)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/metrics.py:14
Function
positional_deprecated
A decorator to nudge users into passing only keyword args (`kwargs`) to the wrapped function, `fn`.
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/utils.py:149
Function
positional_deprecated
A decorator to nudge users into passing only keyword args (`kwargs`) to the wrapped function, `fn`.
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/utils.py:149
Method
post_init
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/qlinear/qlinear_cuda_old.py:95
Method
post_init
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/qlinear/qlinear_triton.py:63
Method
post_init
(self)
inference/compression/dependencies/AutoGPTQ/auto_gptq/nn_modules/qlinear/qlinear_exllama.py:85
Method
predict
(self, inputs)
inference/efficiency/run_efficiency_benchmark.py:32
Method
predict
(self, inputs)
inference/efficiency/dependencies/previous_version/olmo_efficiency.py:71
Method
prep_examples
Overwrite for WinoGrande as multiple ctx, single continuation
olmo/eval/downstream.py:539
← previous
next →
3,001–3,100 of 3,821, ranked by callers