text
stringlengths
7
328k
id
stringlengths
14
166
metadata
dict
__index_level_0__
int64
0
471
# coding=utf-8 # Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/git/test_modeling_git.py/0
{ "file_path": "transformers/tests/models/git/test_modeling_git.py", "repo_id": "transformers", "token_count": 9502 }
400
# coding=utf-8 # Copyright 2021 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/imagegpt/test_modeling_imagegpt.py/0
{ "file_path": "transformers/tests/models/imagegpt/test_modeling_imagegpt.py", "repo_id": "transformers", "token_count": 10579 }
401
# coding=utf-8 # Copyright Iz Beltagy, Matthew E. Peters, Arman Cohan and The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.ap...
transformers/tests/models/led/test_modeling_tf_led.py/0
{ "file_path": "transformers/tests/models/led/test_modeling_tf_led.py", "repo_id": "transformers", "token_count": 6455 }
402
# coding=utf-8 # Copyright 2020 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/megatron_gpt2/test_modeling_megatron_gpt2.py/0
{ "file_path": "transformers/tests/models/megatron_gpt2/test_modeling_megatron_gpt2.py", "repo_id": "transformers", "token_count": 1284 }
403
# coding=utf-8 # Copyright 2021, The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless ...
transformers/tests/models/mvp/test_modeling_mvp.py/0
{ "file_path": "transformers/tests/models/mvp/test_modeling_mvp.py", "repo_id": "transformers", "token_count": 15208 }
404
# coding=utf-8 # Copyright 2022 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/models/oneformer/test_image_processing_oneformer.py/0
{ "file_path": "transformers/tests/models/oneformer/test_image_processing_oneformer.py", "repo_id": "transformers", "token_count": 6432 }
405
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/owlvit/test_modeling_owlvit.py/0
{ "file_path": "transformers/tests/models/owlvit/test_modeling_owlvit.py", "repo_id": "transformers", "token_count": 15261 }
406
# coding=utf-8 # Copyright 2024 The Qwen team, Alibaba Group and The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/...
transformers/tests/models/qwen2/test_modeling_qwen2.py/0
{ "file_path": "transformers/tests/models/qwen2/test_modeling_qwen2.py", "repo_id": "transformers", "token_count": 11644 }
407
# coding=utf-8 # Copyright 2020 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/roberta/test_tokenization_roberta.py/0
{ "file_path": "transformers/tests/models/roberta/test_tokenization_roberta.py", "repo_id": "transformers", "token_count": 7034 }
408
# coding=utf-8 # Copyright 2023 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/sam/test_modeling_sam.py/0
{ "file_path": "transformers/tests/models/sam/test_modeling_sam.py", "repo_id": "transformers", "token_count": 12981 }
409
# coding=utf-8 # Copyright 2024 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/seggpt/test_modeling_seggpt.py/0
{ "file_path": "transformers/tests/models/seggpt/test_modeling_seggpt.py", "repo_id": "transformers", "token_count": 7109 }
410
# Copyright 2021 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/models/speech_to_text/test_processor_speech_to_text.py/0
{ "file_path": "transformers/tests/models/speech_to_text/test_processor_speech_to_text.py", "repo_id": "transformers", "token_count": 2448 }
411
# coding=utf-8 # Copyright 2024 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/stablelm/test_modeling_stablelm.py/0
{ "file_path": "transformers/tests/models/stablelm/test_modeling_stablelm.py", "repo_id": "transformers", "token_count": 11810 }
412
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/timesformer/test_modeling_timesformer.py/0
{ "file_path": "transformers/tests/models/timesformer/test_modeling_timesformer.py", "repo_id": "transformers", "token_count": 5945 }
413
# coding=utf-8 # Copyright 2021 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/models/vilt/test_image_processing_vilt.py/0
{ "file_path": "transformers/tests/models/vilt/test_image_processing_vilt.py", "repo_id": "transformers", "token_count": 2455 }
414
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/x_clip/test_modeling_x_clip.py/0
{ "file_path": "transformers/tests/models/x_clip/test_modeling_x_clip.py", "repo_id": "transformers", "token_count": 12549 }
415
# coding=utf-8 # Copyright 2020 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/xlm_roberta/test_modeling_xlm_roberta.py/0
{ "file_path": "transformers/tests/models/xlm_roberta/test_modeling_xlm_roberta.py", "repo_id": "transformers", "token_count": 1283 }
416
# coding=utf-8 # Copyright 2020 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/optimization/test_optimization.py/0
{ "file_path": "transformers/tests/optimization/test_optimization.py", "repo_id": "transformers", "token_count": 3392 }
417
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/pipelines/test_pipelines_image_to_text.py/0
{ "file_path": "transformers/tests/pipelines/test_pipelines_image_to_text.py", "repo_id": "transformers", "token_count": 5157 }
418
# Copyright 2021 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/pipelines/test_pipelines_zero_shot_image_classification.py/0
{ "file_path": "transformers/tests/pipelines/test_pipelines_zero_shot_image_classification.py", "repo_id": "transformers", "token_count": 5307 }
419
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/repo_utils/test_check_dummies.py/0
{ "file_path": "transformers/tests/repo_utils/test_check_dummies.py", "repo_id": "transformers", "token_count": 1800 }
420
# coding=utf-8 # Copyright 2023 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/test_cache_utils.py/0
{ "file_path": "transformers/tests/test_cache_utils.py", "repo_id": "transformers", "token_count": 9511 }
421
# coding=utf-8 # Copyright 2021 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/test_sequence_feature_extraction_common.py/0
{ "file_path": "transformers/tests/test_sequence_feature_extraction_common.py", "repo_id": "transformers", "token_count": 7929 }
422
# coding=utf-8 # Copyright 2023 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/tools/test_text_summarization.py/0
{ "file_path": "transformers/tests/tools/test_text_summarization.py", "repo_id": "transformers", "token_count": 1135 }
423
# coding=utf-8 # Copyright 2023 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/utils/test_audio_utils.py/0
{ "file_path": "transformers/tests/utils/test_audio_utils.py", "repo_id": "transformers", "token_count": 18583 }
424
# Copyright 2020 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/utils/test_offline.py/0
{ "file_path": "transformers/tests/utils/test_offline.py", "repo_id": "transformers", "token_count": 2916 }
425
import argparse import json import subprocess def get_runner_status(target_runners, token): offline_runners = [] cmd = ( f'curl -H "Accept: application/vnd.github+json" -H "Authorization: Bearer {token}"' " https://api.github.com/repos/huggingface/transformers/actions/runners" ) outpu...
transformers/utils/check_self_hosted_runner.py/0
{ "file_path": "transformers/utils/check_self_hosted_runner.py", "repo_id": "transformers", "token_count": 611 }
426
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/utils/notification_service_doc_tests.py/0
{ "file_path": "transformers/utils/notification_service_doc_tests.py", "repo_id": "transformers", "token_count": 6457 }
427
# coding=utf-8 # Copyright 2021 The HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable...
transformers/utils/tests_fetcher.py/0
{ "file_path": "transformers/utils/tests_fetcher.py", "repo_id": "transformers", "token_count": 22768 }
428
import argparse import math import os import shlex import subprocess import uuid from distutils.util import strtobool import requests def parse_args(): # fmt: off parser = argparse.ArgumentParser() parser.add_argument("--command", type=str, default="", help="the command to run") parser.add_ar...
trl/benchmark/benchmark.py/0
{ "file_path": "trl/benchmark/benchmark.py", "repo_id": "trl", "token_count": 2824 }
429
# Logging As reinforcement learning algorithms are historically challenging to debug, it's important to pay careful attention to logging. By default, the TRL [`PPOTrainer`] saves a lot of relevant information to `wandb` or `tensorboard`. Upon initialization, pass one of these two options to the [`PPOConfig`]: ``` con...
trl/docs/source/logging.mdx/0
{ "file_path": "trl/docs/source/logging.mdx", "repo_id": "trl", "token_count": 1961 }
430
compute_environment: LOCAL_MACHINE debug: false deepspeed_config: deepspeed_multinode_launcher: standard gradient_accumulation_steps: 1 zero3_init_flag: false zero_stage: 1 distributed_type: DEEPSPEED downcast_bf16: 'no' machine_rank: 0 main_training_function: main mixed_precision: 'bf16' num_machines: 1 num_pr...
trl/examples/accelerate_configs/deepspeed_zero1.yaml/0
{ "file_path": "trl/examples/accelerate_configs/deepspeed_zero1.yaml", "repo_id": "trl", "token_count": 171 }
431
from dataclasses import dataclass, field from typing import Any, Dict, List, Optional, Union import evaluate import numpy as np import torch import torch.nn as nn from datasets import load_dataset from peft import LoraConfig, TaskType, get_peft_model from transformers import ( AutoModelForSequenceClassification, ...
trl/examples/research_projects/stack_llama/scripts/reward_modeling.py/0
{ "file_path": "trl/examples/research_projects/stack_llama/scripts/reward_modeling.py", "repo_id": "trl", "token_count": 4554 }
432
# Copyright 2023 metric-space, The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless require...
trl/examples/scripts/ddpo.py/0
{ "file_path": "trl/examples/scripts/ddpo.py", "repo_id": "trl", "token_count": 2705 }
433
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
trl/tests/test_modeling_value_head.py/0
{ "file_path": "trl/tests/test_modeling_value_head.py", "repo_id": "trl", "token_count": 9527 }
434
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
trl/trl/environment/base_environment.py/0
{ "file_path": "trl/trl/environment/base_environment.py", "repo_id": "trl", "token_count": 7661 }
435
# Copyright 2023 DDPO-pytorch authors (Kevin Black), metric-space, The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/lic...
trl/trl/trainer/ddpo_trainer.py/0
{ "file_path": "trl/trl/trainer/ddpo_trainer.py", "repo_id": "trl", "token_count": 12350 }
436
# Builds GPU docker image of PyTorch specifically # Uses multi-staged approach to reduce size # Stage 1 # Use base conda image to reduce time FROM continuumio/miniconda3:latest AS compile-image # Specify py version ENV PYTHON_VERSION=3.9 # Install apt libs RUN apt-get update && \ apt-get install -y curl git wget &&...
accelerate/docker/accelerate-gpu/Dockerfile/0
{ "file_path": "accelerate/docker/accelerate-gpu/Dockerfile", "repo_id": "accelerate", "token_count": 539 }
0
<!--Copyright 2023 The HuggingFace Team. All rights reserved. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed...
accelerate/docs/source/concept_guides/low_precision_training.md/0
{ "file_path": "accelerate/docs/source/concept_guides/low_precision_training.md", "repo_id": "accelerate", "token_count": 1466 }
1
<!--Copyright 2021 The HuggingFace Team. All rights reserved. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed...
accelerate/docs/source/package_reference/state.md/0
{ "file_path": "accelerate/docs/source/package_reference/state.md", "repo_id": "accelerate", "token_count": 291 }
2
<!--Copyright 2022 The HuggingFace Team. All rights reserved. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed...
accelerate/docs/source/usage_guides/model_size_estimator.md/0
{ "file_path": "accelerate/docs/source/usage_guides/model_size_estimator.md", "repo_id": "accelerate", "token_count": 2030 }
3
# Copyright 2024 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by appl...
accelerate/examples/inference/llama.py/0
{ "file_path": "accelerate/examples/inference/llama.py", "repo_id": "accelerate", "token_count": 706 }
4
# Copyright 2021 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/src/accelerate/accelerator.py/0
{ "file_path": "accelerate/src/accelerate/accelerator.py", "repo_id": "accelerate", "token_count": 63109 }
5
# Copyright 2021 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/src/accelerate/optimizer.py/0
{ "file_path": "accelerate/src/accelerate/optimizer.py", "repo_id": "accelerate", "token_count": 3247 }
6
#!/usr/bin/env python # Copyright 2023 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unles...
accelerate/src/accelerate/test_utils/scripts/test_ops.py/0
{ "file_path": "accelerate/src/accelerate/test_utils/scripts/test_ops.py", "repo_id": "accelerate", "token_count": 2347 }
7
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/src/accelerate/utils/memory.py/0
{ "file_path": "accelerate/src/accelerate/utils/memory.py", "repo_id": "accelerate", "token_count": 2210 }
8
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/tests/test_big_modeling.py/0
{ "file_path": "accelerate/tests/test_big_modeling.py", "repo_id": "accelerate", "token_count": 19558 }
9
# Copyright 2022 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/tests/test_modeling_utils.py/0
{ "file_path": "accelerate/tests/test_modeling_utils.py", "repo_id": "accelerate", "token_count": 14814 }
10
# Copyright 2022 The HuggingFace Team, the AllenNLP library authors. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # ...
accelerate/utils/stale.py/0
{ "file_path": "accelerate/utils/stale.py", "repo_id": "accelerate", "token_count": 1013 }
11
# Model arguments model_name_or_path: BramVanroy/gpt2-cpt-dutch model_revision: main torch_dtype: bfloat16 # Data training arguments chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|syst...
alignment-handbook/recipes/gpt2-nl/sft/config_full.yaml/0
{ "file_path": "alignment-handbook/recipes/gpt2-nl/sft/config_full.yaml", "repo_id": "alignment-handbook", "token_count": 553 }
12
# Model arguments model_name_or_path: google/gemma-7b model_revision: main tokenizer_name_or_path: philschmid/gemma-tokenizer-chatml # Custom tokenizer with <|im_start|> and <|im_end|> tokens torch_dtype: bfloat16 use_flash_attention_2: true # Data training arguments dataset_mixer: HuggingFaceH4/deita-10k-v0-sft: 1....
alignment-handbook/recipes/zephyr-7b-gemma/sft/config_full.yaml/0
{ "file_path": "alignment-handbook/recipes/zephyr-7b-gemma/sft/config_full.yaml", "repo_id": "alignment-handbook", "token_count": 480 }
13
# Copyright 2023 The HuggingFace Team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
alignment-handbook/tests/test_configs.py/0
{ "file_path": "alignment-handbook/tests/test_configs.py", "repo_id": "alignment-handbook", "token_count": 697 }
14
# Hello world! We will now create the hello world of the ML world, building a model capable of solving MNIST dataset. Open `src/main.rs` and fill in this content: ```rust # extern crate candle_core; use candle_core::{Device, Result, Tensor}; struct Model { first: Tensor, second: Tensor, } impl Model { ...
candle/candle-book/src/guide/hello_world.md/0
{ "file_path": "candle/candle-book/src/guide/hello_world.md", "repo_id": "candle", "token_count": 2069 }
15
# candle Minimalist ML framework for Rust
candle/candle-core/README.md/0
{ "file_path": "candle/candle-core/README.md", "repo_id": "candle", "token_count": 11 }
16
use super::{Cpu, CpuF16}; #[cfg(target_arch = "x86")] use core::arch::x86::*; #[cfg(target_arch = "x86_64")] use core::arch::x86_64::*; use half::f16; pub struct CurrentCpu {} const STEP: usize = 32; const EPR: usize = 8; const ARR: usize = STEP / EPR; impl Cpu<ARR> for CurrentCpu { type Unit = __m256; type...
candle/candle-core/src/cpu/avx.rs/0
{ "file_path": "candle/candle-core/src/cpu/avx.rs", "repo_id": "candle", "token_count": 2094 }
17
//! Types for elements that can be stored and manipulated using tensors. #![allow(clippy::redundant_closure_call)] use crate::backend::BackendStorage; use crate::{CpuStorage, Error, Result}; /// The different types of elements allowed in tensors. #[derive(Debug, Copy, Clone, PartialEq, Eq, Hash)] pub enum DType { ...
candle/candle-core/src/dtype.rs/0
{ "file_path": "candle/candle-core/src/dtype.rs", "repo_id": "candle", "token_count": 2984 }
18
#![allow(unused)] use super::GgmlDType; use crate::{Error, MetalDevice, MetalStorage, Result}; pub struct QMetalStorage { dtype: GgmlDType, device: MetalDevice, } impl QMetalStorage { pub fn zeros(_: &MetalDevice, _: usize, _: GgmlDType) -> Result<Self> { Err(Error::NotCompiledWithMetalSupport) ...
candle/candle-core/src/quantized/dummy_metal.rs/0
{ "file_path": "candle/candle-core/src/quantized/dummy_metal.rs", "repo_id": "candle", "token_count": 522 }
19
use crate::{Result, Tensor}; #[macro_export] macro_rules! test_device { // TODO: Switch to generating the two last arguments automatically once concat_idents is // stable. https://github.com/rust-lang/rust/issues/29599 ($fn_name: ident, $test_cpu: ident, $test_cuda: ident, $test_metal: ident) => { ...
candle/candle-core/src/test_utils.rs/0
{ "file_path": "candle/candle-core/src/test_utils.rs", "repo_id": "candle", "token_count": 923 }
20
use candle_core::{DType, Result, Tensor}; #[test] fn npy() -> Result<()> { let npy = Tensor::read_npy("tests/test.npy")?; assert_eq!( npy.to_dtype(DType::U8)?.to_vec1::<u8>()?, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] ); Ok(()) } #[test] fn npz() -> Result<()> { let npz = Tensor::read_npz("t...
candle/candle-core/tests/serialization_tests.rs/0
{ "file_path": "candle/candle-core/tests/serialization_tests.rs", "repo_id": "candle", "token_count": 333 }
21
[package] name = "candle-examples" version.workspace = true edition.workspace = true description.workspace = true repository.workspace = true keywords.workspace = true categories.workspace = true license.workspace = true readme = "README.md" [dependencies] accelerate-src = { workspace = true, optional = true } candle ...
candle/candle-examples/Cargo.toml/0
{ "file_path": "candle/candle-examples/Cargo.toml", "repo_id": "candle", "token_count": 1092 }
22
#include <stdint.h> #include "reduction_utils.cuh" template <typename scalar_t> __device__ void rms_norm_kernel(scalar_t *__restrict__ out, // [num_tokens, hidden_size] const scalar_t *__restrict__ input, // [num_tokens, hidden_size] const float epsilon, const uint32_t num_token...
candle/candle-examples/examples/custom-ops/kernels/layernorm_kernels.cu/0
{ "file_path": "candle/candle-examples/examples/custom-ops/kernels/layernorm_kernels.cu", "repo_id": "candle", "token_count": 561 }
23
# candle-gemma: 2b and 7b LLMs from Google DeepMind [Gemma](https://ai.google.dev/gemma/docs) is a collection of lightweight open models published by Google Deepmind with a 2b and a 7b variant. In order to use the example below, you have to accept the license on the [HuggingFace Hub Gemma repo](https://huggingface.co...
candle/candle-examples/examples/gemma/README.md/0
{ "file_path": "candle/candle-examples/examples/gemma/README.md", "repo_id": "candle", "token_count": 351 }
24
#[cfg(feature = "mkl")] extern crate intel_mkl_src; #[cfg(feature = "accelerate")] extern crate accelerate_src; use anyhow::Error as E; use clap::{Parser, ValueEnum}; use candle::{DType, Tensor}; use candle_examples::token_output_stream::TokenOutputStream; use candle_nn::VarBuilder; use candle_transformers::models::...
candle/candle-examples/examples/marian-mt/main.rs/0
{ "file_path": "candle/candle-examples/examples/marian-mt/main.rs", "repo_id": "candle", "token_count": 2385 }
25
use anyhow::Result; use candle::{Device, Tensor}; use clap::{Parser, Subcommand}; #[derive(Subcommand, Debug, Clone)] enum Command { Print { #[arg(long)] file: String, }, SimpleEval { #[arg(long)] file: String, }, } #[derive(Parser, Debug)] #[command(author, version, a...
candle/candle-examples/examples/onnx_basics.rs/0
{ "file_path": "candle/candle-examples/examples/onnx_basics.rs", "repo_id": "candle", "token_count": 2016 }
26
use super::gym_env::{GymEnv, Step}; use candle::{DType, Device, Error, Module, Result, Tensor}; use candle_nn::{ linear, ops::log_softmax, ops::softmax, sequential::seq, Activation, AdamW, Optimizer, ParamsAdamW, VarBuilder, VarMap, }; use rand::{distributions::Distribution, rngs::ThreadRng, Rng}; fn new_model...
candle/candle-examples/examples/reinforcement-learning/policy_gradient.rs/0
{ "file_path": "candle/candle-examples/examples/reinforcement-learning/policy_gradient.rs", "repo_id": "candle", "token_count": 2333 }
27
## VGG Model Implementation This example demonstrates the implementation of VGG models (VGG13, VGG16, VGG19) using the Candle library. The VGG models are defined in `candle-transformers/src/models/vgg.rs`. The main function in `candle-examples/examples/vgg/main.rs` loads an image, selects the VGG model based on the p...
candle/candle-examples/examples/vgg/README.md/0
{ "file_path": "candle/candle-examples/examples/vgg/README.md", "repo_id": "candle", "token_count": 200 }
28
#[cfg(feature = "mkl")] extern crate intel_mkl_src; #[cfg(feature = "accelerate")] extern crate accelerate_src; use anyhow::{Error as E, Result}; use clap::{Parser, ValueEnum}; use candle_transformers::models::yi::{Config, Model}; use candle::{DType, Device, Tensor}; use candle_examples::token_output_stream::TokenO...
candle/candle-examples/examples/yi/main.rs/0
{ "file_path": "candle/candle-examples/examples/yi/main.rs", "repo_id": "candle", "token_count": 3580 }
29
pub mod audio; pub mod bs1770; pub mod coco_classes; pub mod imagenet; pub mod token_output_stream; pub mod wav; use candle::utils::{cuda_is_available, metal_is_available}; use candle::{Device, Result, Tensor}; pub fn device(cpu: bool) -> Result<Device> { if cpu { Ok(Device::Cpu) } else if cuda_is_ava...
candle/candle-examples/src/lib.rs/0
{ "file_path": "candle/candle-examples/src/lib.rs", "repo_id": "candle", "token_count": 2455 }
30
// Inspired by // https://github.com/NVIDIA/DALI/blob/main/include/dali/core/static_switch.h // and https://github.com/pytorch/pytorch/blob/master/aten/src/ATen/Dispatch.h #pragma once /// @param COND - a boolean expression to switch by /// @param CONST_NAME - a name given for the constexpr bool variable. /// @...
candle/candle-flash-attn/kernels/static_switch.h/0
{ "file_path": "candle/candle-flash-attn/kernels/static_switch.h", "repo_id": "candle", "token_count": 1516 }
31
// WARNING: THIS IS ONLY VALID ASSUMING THAT inp IS CONTIGUOUS! // TODO: proper error reporting when ids are larger than v_size. #include "cuda_utils.cuh" #include<stdint.h> template<typename T, typename I> __device__ void index_select( const size_t numel, const size_t num_dims, const size_t *info, con...
candle/candle-kernels/src/indexing.cu/0
{ "file_path": "candle/candle-kernels/src/indexing.cu", "repo_id": "candle", "token_count": 4357 }
32
#include <metal_stdlib> #include <metal_integer> #include <metal_atomic> using namespace metal; // Constants // 2^32 and 1/2^32. Useful for converting between float and uint. static constexpr constant ulong UNIF01_NORM32 = 4294967296; static constexpr constant float UNIF01_INV32 = 2.328306436538696289e-10; // 2 * pi ...
candle/candle-metal-kernels/src/random.metal/0
{ "file_path": "candle/candle-metal-kernels/src/random.metal", "repo_id": "candle", "token_count": 3671 }
33
#[cfg(feature = "mkl")] extern crate intel_mkl_src; #[cfg(feature = "accelerate")] extern crate accelerate_src; use candle::{DType, Device, Result, Tensor}; use candle_nn::{linear, AdamW, Linear, Module, Optimizer, ParamsAdamW, VarBuilder, VarMap}; fn gen_data() -> Result<(Tensor, Tensor)> { // Generate some sam...
candle/candle-nn/examples/basic_optimizer.rs/0
{ "file_path": "candle/candle-nn/examples/basic_optimizer.rs", "repo_id": "candle", "token_count": 595 }
34
//! Recurrent Neural Networks use candle::{DType, Device, IndexOp, Result, Tensor}; /// Trait for Recurrent Neural Networks. #[allow(clippy::upper_case_acronyms)] pub trait RNN { type State: Clone; /// A zero state from which the recurrent network is usually initialized. fn zero_state(&self, batch_dim: us...
candle/candle-nn/src/rnn.rs/0
{ "file_path": "candle/candle-nn/src/rnn.rs", "repo_id": "candle", "token_count": 4879 }
35
use crate::onnx; use crate::onnx::attribute_proto::AttributeType; use crate::onnx::tensor_proto::DataType; use candle::{bail, DType, Device, Result, Tensor}; use std::collections::HashMap; pub type Value = Tensor; pub fn dtype(dt: DataType) -> Option<DType> { match dt { DataType::Uint8 => Some(DType::U8),...
candle/candle-onnx/src/eval.rs/0
{ "file_path": "candle/candle-onnx/src/eval.rs", "repo_id": "candle", "token_count": 21412 }
36
import candle from typing import Dict, Tuple, Any from candle import Tensor, QTensor, utils, nn from candle.nn import Module, ModuleList def masked_fill(on_false: Tensor, mask: Tensor, on_true: Tensor): shape = mask.shape on_true = candle.tensor(on_true).broadcast_as(shape) return mask.where_cond(on_true,...
candle/candle-pyo3/py_src/candle/models/llama.py/0
{ "file_path": "candle/candle-pyo3/py_src/candle/models/llama.py", "repo_id": "candle", "token_count": 2981 }
37
#![allow(clippy::redundant_closure_call)] use pyo3::exceptions::{PyTypeError, PyValueError}; use pyo3::prelude::*; use pyo3::pyclass::CompareOp; use pyo3::types::{IntoPyDict, PyDict, PyTuple}; use pyo3::ToPyObject; use std::collections::hash_map::DefaultHasher; use std::hash::{Hash, Hasher}; use std::os::raw::c_long; u...
candle/candle-pyo3/src/lib.rs/0
{ "file_path": "candle/candle-pyo3/src/lib.rs", "repo_id": "candle", "token_count": 29734 }
38
use candle::{DType, Error, Result, Tensor}; use rand::{distributions::Distribution, SeedableRng}; #[derive(Clone, PartialEq, Debug)] pub enum Sampling { ArgMax, All { temperature: f64 }, TopK { k: usize, temperature: f64 }, TopP { p: f64, temperature: f64 }, TopKThenTopP { k: usize, p: f64, tempera...
candle/candle-transformers/src/generation/mod.rs/0
{ "file_path": "candle/candle-transformers/src/generation/mod.rs", "repo_id": "candle", "token_count": 2910 }
39
#![allow(unused)] use candle::{DType, IndexOp, Layout, Module, Result, Shape, Tensor, D}; use candle_nn::{conv1d, Conv1d, Conv1dConfig, ConvTranspose1d, VarBuilder}; // Encodec Model // https://github.com/huggingface/transformers/blob/main/src/transformers/models/encodec/modeling_encodec.py #[derive(Debug, Copy, Clon...
candle/candle-transformers/src/models/encodec.rs/0
{ "file_path": "candle/candle-transformers/src/models/encodec.rs", "repo_id": "candle", "token_count": 12642 }
40
use crate::models::with_tracing::{linear_no_bias, Embedding, Linear}; /// MPT model used by replit-code-v1_5-3b /// https://huggingface.co/replit/replit-code-v1_5-3b/blob/main/modeling_mpt.py use candle::{DType, Device, IndexOp, Module, Result, Tensor, D}; use candle_nn::{layer_norm, LayerNorm, VarBuilder}; // https:/...
candle/candle-transformers/src/models/mpt.rs/0
{ "file_path": "candle/candle-transformers/src/models/mpt.rs", "repo_id": "candle", "token_count": 5485 }
41
//! # Denoising Diffusion Implicit Models //! //! The Denoising Diffusion Implicit Models (DDIM) is a simple scheduler //! similar to Denoising Diffusion Probabilistic Models (DDPM). The DDPM //! generative process is the reverse of a Markovian process, DDIM generalizes //! this to non-Markovian guidance. //! //! Denoi...
candle/candle-transformers/src/models/stable_diffusion/ddim.rs/0
{ "file_path": "candle/candle-transformers/src/models/stable_diffusion/ddim.rs", "repo_id": "candle", "token_count": 3953 }
42
use crate::models::with_tracing::{conv2d, linear, linear_no_bias, Conv2d, Linear}; use candle::{IndexOp, Module, Result, Tensor, D}; use candle_nn::{layer_norm, LayerNorm, VarBuilder}; // https://github.com/huggingface/transformers/blob/main/src/transformers/models/vit/configuration_vit.py #[derive(Debug, Clone, serde...
candle/candle-transformers/src/models/vit.rs/0
{ "file_path": "candle/candle-transformers/src/models/vit.rs", "repo_id": "candle", "token_count": 5870 }
43
use candle::{DType, Device, IndexOp, Result, Tensor, D}; use candle_nn::{ embedding, linear_no_bias as linear, rms_norm, Embedding, Linear, Module, RmsNorm, VarBuilder, }; use std::collections::HashMap; use std::sync::{Arc, Mutex}; #[derive(Debug, Clone)] pub struct Config { pub dim: usize, // transform...
candle/candle-wasm-examples/llama2-c/src/model.rs/0
{ "file_path": "candle/candle-wasm-examples/llama2-c/src/model.rs", "repo_id": "candle", "token_count": 5272 }
44
use wasm_bindgen::prelude::*; #[wasm_bindgen] extern "C" { // Use `js_namespace` here to bind `console.log(..)` instead of just // `log(..)` #[wasm_bindgen(js_namespace = console)] pub fn log(s: &str); } #[macro_export] macro_rules! console_log { // Note that this is using the `log` function impor...
candle/candle-wasm-examples/phi/src/lib.rs/0
{ "file_path": "candle/candle-wasm-examples/phi/src/lib.rs", "repo_id": "candle", "token_count": 183 }
45
//load the candle Whisper decoder wasm module import init, { Decoder } from "./build/m.js"; async function fetchArrayBuffer(url) { const cacheName = "whisper-candle-cache"; const cache = await caches.open(cacheName); const cachedResponse = await cache.match(url); if (cachedResponse) { const data = await ca...
candle/candle-wasm-examples/whisper/whisperWorker.js/0
{ "file_path": "candle/candle-wasm-examples/whisper/whisperWorker.js", "repo_id": "candle", "token_count": 1215 }
46
Run the tests with: ```bash RUST_LOG=wasm_bindgen_test_runner wasm-pack test --chrome --headless ``` Or: ```bash wasm-pack test --chrome ``` If you get an "invalid session id" failure in headless mode, check that logs and it may well be that your ChromeDriver is not at the same version as your browser.
candle/candle-wasm-tests/README.md/0
{ "file_path": "candle/candle-wasm-tests/README.md", "repo_id": "candle", "token_count": 98 }
47
# syntax=docker/dockerfile:1 # read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker # you will also find guides on how best to write your Dockerfile FROM node:20 as builder-production WORKDIR /app COPY --link --chown=1000 package-lock.json package.json ./ RUN --mount=type=cache,target=/app/.npm \ ...
chat-ui/Dockerfile/0
{ "file_path": "chat-ui/Dockerfile", "repo_id": "chat-ui", "token_count": 351 }
48
import { ADMIN_API_SECRET, COOKIE_NAME, ENABLE_ASSISTANTS, EXPOSE_API, MESSAGES_BEFORE_LOGIN, PARQUET_EXPORT_SECRET, } from "$env/static/private"; import type { Handle } from "@sveltejs/kit"; import { PUBLIC_GOOGLE_ANALYTICS_ID, PUBLIC_ORIGIN, PUBLIC_APP_DISCLAIMER, } from "$env/static/public"; import { collec...
chat-ui/src/hooks.server.ts/0
{ "file_path": "chat-ui/src/hooks.server.ts", "repo_id": "chat-ui", "token_count": 1944 }
49
<script lang="ts"> import CarbonEarth from "~icons/carbon/earth"; import CarbonArrowUpRight from "~icons/carbon/arrow-up-right"; import type { Model } from "$lib/types/Model"; export let model: Pick<Model, "name" | "datasetName" | "websiteUrl" | "modelUrl" | "datasetUrl">; export let variant: "light" | "dark" = ...
chat-ui/src/lib/components/ModelCardMetadata.svelte/0
{ "file_path": "chat-ui/src/lib/components/ModelCardMetadata.svelte", "repo_id": "chat-ui", "token_count": 623 }
50
<script lang="ts"> import { webSearchParameters } from "$lib/stores/webSearchParameters"; import CarbonInformation from "~icons/carbon/information"; import Switch from "./Switch.svelte"; const toggle = () => ($webSearchParameters.useSearch = !$webSearchParameters.useSearch); </script> <div class="flex h-8 cursor...
chat-ui/src/lib/components/WebSearchToggle.svelte/0
{ "file_path": "chat-ui/src/lib/components/WebSearchToggle.svelte", "repo_id": "chat-ui", "token_count": 447 }
51
import { collections } from "$lib/server/database"; import { ObjectId } from "mongodb"; /** * Returns the lock id if the lock was acquired, false otherwise */ export async function acquireLock(key: string): Promise<ObjectId | false> { try { const id = new ObjectId(); const insert = await collections.semaphores...
chat-ui/src/lib/migrations/lock.ts/0
{ "file_path": "chat-ui/src/lib/migrations/lock.ts", "repo_id": "chat-ui", "token_count": 400 }
52
import { z } from "zod"; import { COHERE_API_TOKEN } from "$env/static/private"; import type { Endpoint } from "../endpoints"; import type { TextGenerationStreamOutput } from "@huggingface/inference"; import type { Cohere, CohereClient } from "cohere-ai"; import { buildPrompt } from "$lib/buildPrompt"; export const en...
chat-ui/src/lib/server/endpoints/cohere/endpointCohere.ts/0
{ "file_path": "chat-ui/src/lib/server/endpoints/cohere/endpointCohere.ts", "repo_id": "chat-ui", "token_count": 1331 }
53
import { dot } from "@xenova/transformers"; import type { EmbeddingBackendModel } from "$lib/server/embeddingModels"; import type { Embedding } from "$lib/server/embeddingEndpoints/embeddingEndpoints"; // see here: https://github.com/nmslib/hnswlib/blob/359b2ba87358224963986f709e593d799064ace6/README.md?plain=1#L34 fu...
chat-ui/src/lib/server/sentenceSimilarity.ts/0
{ "file_path": "chat-ui/src/lib/server/sentenceSimilarity.ts", "repo_id": "chat-ui", "token_count": 497 }
54
import { writable } from "svelte/store"; export interface WebSearchParameters { useSearch: boolean; nItems: number; } export const webSearchParameters = writable<WebSearchParameters>({ useSearch: false, nItems: 5, });
chat-ui/src/lib/stores/webSearchParameters.ts/0
{ "file_path": "chat-ui/src/lib/stores/webSearchParameters.ts", "repo_id": "chat-ui", "token_count": 68 }
55
import { defaultModel } from "$lib/server/models"; import type { Assistant } from "./Assistant"; import type { Timestamps } from "./Timestamps"; import type { User } from "./User"; export interface Settings extends Timestamps { userId?: User["_id"]; sessionId?: string; /** * Note: Only conversations with this se...
chat-ui/src/lib/types/Settings.ts/0
{ "file_path": "chat-ui/src/lib/types/Settings.ts", "repo_id": "chat-ui", "token_count": 289 }
56
import { base } from "$app/paths"; import { PUBLIC_ORIGIN, PUBLIC_SHARE_PREFIX } from "$env/static/public"; export function getShareUrl(url: URL, shareId: string): string { return `${PUBLIC_SHARE_PREFIX || `${PUBLIC_ORIGIN || url.origin}${base}`}/r/${shareId}`; }
chat-ui/src/lib/utils/getShareUrl.ts/0
{ "file_path": "chat-ui/src/lib/utils/getShareUrl.ts", "repo_id": "chat-ui", "token_count": 99 }
57
export const timeout = <T>(prom: Promise<T>, time: number): Promise<T> => { let timer: NodeJS.Timeout; return Promise.race([prom, new Promise<T>((_r, rej) => (timer = setTimeout(rej, time)))]).finally( () => clearTimeout(timer) ); };
chat-ui/src/lib/utils/timeout.ts/0
{ "file_path": "chat-ui/src/lib/utils/timeout.ts", "repo_id": "chat-ui", "token_count": 87 }
58
import { PARQUET_EXPORT_DATASET, PARQUET_EXPORT_HF_TOKEN } from "$env/static/private"; import { collections } from "$lib/server/database"; import type { Message } from "$lib/types/Message"; import { error } from "@sveltejs/kit"; import { pathToFileURL } from "node:url"; import { unlink } from "node:fs/promises"; import...
chat-ui/src/routes/admin/export/+server.ts/0
{ "file_path": "chat-ui/src/routes/admin/export/+server.ts", "repo_id": "chat-ui", "token_count": 1653 }
59
<script lang="ts"> import ChatWindow from "$lib/components/chat/ChatWindow.svelte"; import { pendingMessage } from "$lib/stores/pendingMessage"; import { isAborted } from "$lib/stores/isAborted"; import { onMount } from "svelte"; import { page } from "$app/stores"; import { goto, invalidateAll } from "$app/naviga...
chat-ui/src/routes/conversation/[id]/+page.svelte/0
{ "file_path": "chat-ui/src/routes/conversation/[id]/+page.svelte", "repo_id": "chat-ui", "token_count": 4558 }
60
import ModelThumbnail from "./ModelThumbnail.svelte"; import { redirect, type RequestHandler } from "@sveltejs/kit"; import type { SvelteComponent } from "svelte"; import { Resvg } from "@resvg/resvg-js"; import satori from "satori"; import { html } from "satori-html"; import InterRegular from "../../../../../static/...
chat-ui/src/routes/models/[...model]/thumbnail.png/+server.ts/0
{ "file_path": "chat-ui/src/routes/models/[...model]/thumbnail.png/+server.ts", "repo_id": "chat-ui", "token_count": 526 }
61
<svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none"> <path fill="#FFD21E" d="M4 15.55C4 9.72 8.72 5 14.55 5h4.11a9.34 9.34 0 1 1 0 18.68H7.58l-2.89 2.8a.41.41 0 0 1-.69-.3V15.55Z" /> <path fill="#32343D" d="M19.63 12.48c.37.14.52.9.9.7.71-.38.98-1.27.6-1.98a1.46 1.46 0 0 0-1.98-.61 1.4...
chat-ui/static/huggingchat/logo.svg/0
{ "file_path": "chat-ui/static/huggingchat/logo.svg", "repo_id": "chat-ui", "token_count": 523 }
62