path	# lines of code	# active days	days since first update	days since last update	# commits	# contributors	first updated	last updated	first contributor	last contributor
toolkits/multimodal_data_preprocessing/convert_llava_pretrain_to_wds.py	25	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/multimodal_data_preprocessing/build_llava_frame_dataset.py	123	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/multimodal_data_preprocessing/replace_llava_image_key.py	29	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/multimodal_data_preprocessing/convert_custom_dataset_to_wds_chatml.py	98	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/pretrain_data_preprocessing/preprocess_data.py	198	6	619	161	6	3	2023-09-04	2024-12-05	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/pretrain_data_preprocessing/clean_raw_text.py	69	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/pretrain_data_preprocessing/convert_json_to_list.py	10	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/pretrain_data_preprocessing/qwen_hf_preprocess_datasets.py	86	1	473	473	1	1	2024-01-28	2024-01-28	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/pretrain_data_preprocessing/preprocess_wudao2.py	76	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/pretrain_data_preprocessing/preprocess_data_megatron.py	360	10	395	16	10	4	2024-04-15	2025-04-29	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/general/synchronizer.py	119	3	30	3	3	1	2025-04-15	2025-05-12	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/general/__init__.py	6	1	30	30	1	1	2025-04-15	2025-04-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/general/h2m_synchronizer.py	259	2	30	3	2	1	2025-04-15	2025-05-12	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/general/m2h_synchronizer.py	499	2	30	3	2	1	2025-04-15	2025-05-12	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/convert.py	80	1	30	30	1	1	2025-04-15	2025-04-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/deepseek_v3/__init__.py	6	1	30	30	1	1	2025-04-15	2025-04-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/deepseek_v3/patch.py	25	1	30	30	1	1	2025-04-15	2025-04-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/deepseek_v3/h2m_synchronizer.py	46	1	30	30	1	1	2025-04-15	2025-04-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/distributed_checkpoints_convertor/impl/deepseek_v3/m2h_synchronizer.py	42	1	30	30	1	1	2025-04-15	2025-04-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/sft_data_preprocessing/sample_stats.py	23	2	295	42	2	1	2024-07-24	2025-04-03	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/sft_data_preprocessing/build_idxmap_sft_dataset.py	319	5	245	92	5	1	2024-09-12	2025-02-12	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/auto_configurator/report_theoretical_memory.py	147	1	197	197	1	1	2024-10-30	2024-10-30	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/auto_configurator/report_auto_config.py	124	1	197	197	1	1	2024-10-30	2024-10-30	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/falcon40b/configuration_RW.py	50	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/falcon40b/checkpoint_reshaping_and_interoperability.py	583	2	619	468	2	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/glm130b/merge_130b_ckpts.py	96	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/glm130b/checkpoint_reshaping_and_interoperability.py	363	2	619	468	2	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/chatglm/checkpoint_reshaping_and_interoperability.py	396	2	619	468	2	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/llava/hf2mcore_llava.py	669	1	175	175	2	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/utils/__init__.py	146	6	118	42	6	2	2025-01-17	2025-04-03	46404040+lostkevin@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/mistral/hf2mcore_mixtral.py	672	4	388	83	4	2	2024-04-22	2025-02-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/mistral/hf2mcore.py	468	5	389	83	6	2	2024-04-21	2025-02-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/baichuan/configuration_baichuan.py	43	1	608	608	1	1	2023-09-15	2023-09-15	38210876+lwmlyy@users.noreply.github.com	38210876+lwmlyy@users.noreply.github.com
toolkits/model_checkpoints_convertor/baichuan/hf2te.py	378	5	619	468	5	2	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/baichuan/checkpoint_reshaping_and_interoperability.py	649	8	619	468	8	2	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/deepseek/hf2mcore_deepseek_v2_moe.py	454	13	353	71	13	3	2024-05-27	2025-03-05	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/deepseek/hf2mcore_deepseek_v3_moe.py	578	13	83	42	14	2	2025-02-21	2025-04-03	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/deepseek/fp8_cast_bf16.py	88	1	79	79	1	1	2025-02-25	2025-02-25	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/bloom/deepspeed_to_megatron_ori.py	149	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/bloom/checkpoint_reshaping_and_interoperability.py	572	3	619	468	3	2	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/bloom/deepspeed_to_megatron.py	149	2	619	468	2	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/bloom/reward_model_to_megatron.py	573	3	619	468	3	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/galactica/checkpoint_reshaping_and_interoperability.py	454	4	619	468	4	2	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/llama/hf_llama_moe/llama_moe.py	19	2	444	383	3	2	2024-02-26	2024-04-27	1208266117@qq.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/llama/hf2megatron.py	808	4	389	206	5	2	2024-04-21	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/llama/hf2mcore_llama3_1.py	710	3	265	83	3	2	2024-08-23	2025-02-21	46404040+lostkevin@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/llama/hf2mcore.py	674	3	389	206	4	2	2024-04-21	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/llama/hf2mcore_70b.py	577	4	388	206	4	3	2024-04-22	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/baichuan2/configuration_baichuan.py	43	1	604	604	1	1	2023-09-19	2023-09-19	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/baichuan2/hf2te.py	360	5	574	468	5	2	2023-10-19	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/baichuan2/checkpoint_reshaping_and_interoperability.py	638	11	604	395	14	4	2023-09-19	2024-04-15	38210876+lwmlyy@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/falcon/configuration_RW.py	101	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/falcon/checkpoint_reshaping_and_interoperability.py	612	2	619	468	2	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/yi/checkpoint_reshaping_and_interoperability.py	468	3	544	468	3	1	2023-11-18	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen2_dense_and_moe_gqa.py	821	12	330	83	15	5	2024-06-19	2025-02-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen2.5_vl.py	607	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_dense_gqa.py	593	2	367	206	2	2	2024-05-13	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_dense_mha.py	280	3	367	206	3	3	2024-05-13	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen2_moe.py	555	3	51	16	3	3	2025-03-25	2025-04-29	wanqian5@tal.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.0.py	725	2	389	206	2	2	2024-04-21	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_moe.py	479	5	367	206	5	3	2024-05-13	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen2_vl.py	616	9	169	57	9	2	2024-11-27	2025-03-19	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.5.py	810	4	389	206	4	4	2024-04-21	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2megablocks_qwen1.5.py	546	2	389	206	2	2	2024-04-21	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_dense_mha_to_moe.py	227	3	367	206	3	3	2024-05-13	2024-10-21	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
toolkits/model_checkpoints_convertor/glm/checkpoint_reshaping_and_interoperability.py	378	2	619	468	2	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
toolkits/model_checkpoints_convertor/starcoder/checkpoint_reshaping_and_interoperability.py	583	3	619	468	3	2	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
rlhf/deepspeed-chat/rm_main.py	319	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
rlhf/deepspeed-chat/utils.py	204	1	616	616	1	1	2023-09-07	2023-09-07	bdshichen@sina.cn	bdshichen@sina.cn
rlhf/trlx/reward_model_bloom.py	81	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
rlhf/trlx/train_reward_model_bloom.py	151	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
rlhf/trlx/trlx_bloom_rlhf.py	178	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/generation/gpt_predictor.py	74	2	619	473	2	1	2023-09-04	2024-01-28	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/generation/tokenization.py	76	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/generation/generation.py	317	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/generation/api.py	170	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/data/__init__.py	88	12	552	78	12	3	2023-11-10	2025-02-26	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/data/energon/chatml.py	46	1	139	139	1	1	2024-12-27	2024-12-27	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/data/json_sft.py	106	1	83	83	1	1	2025-02-21	2025-02-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/data/image_processing.py	67	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/data/utils.py	318	20	473	45	20	3	2024-01-28	2025-03-31	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/data/dataset_helpers.py	381	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/layer_specs.py	95	2	169	83	2	2	2024-11-27	2025-02-21	46404040+lostkevin@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2_vl/visionmodel.py	160	2	169	139	2	1	2024-11-27	2024-12-27	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/gpt_model.py	143	2	169	120	2	1	2024-11-27	2025-01-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/attention.py	530	2	169	83	2	2	2024-11-27	2025-02-21	46404040+lostkevin@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2_vl/language_module.py	104	1	169	169	1	1	2024-11-27	2024-11-27	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/language_model_embedding.py	98	1	120	120	1	1	2025-01-15	2025-01-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/attention_vision.py	529	2	169	83	2	2	2024-11-27	2025-02-21	46404040+lostkevin@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2_vl/rotary_pos_embedding.py	145	2	169	120	2	1	2024-11-27	2025-01-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/transformer_config.py	53	3	169	118	3	1	2024-11-27	2025-01-17	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/rope_utils.py	108	2	169	139	2	1	2024-11-27	2024-12-27	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_vl/model.py	191	3	169	120	3	1	2024-11-27	2025-01-15	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/falcon40b/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/falcon40b/gpt_model.py	94	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/falcon40b/language_model.py	491	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/falcon40b/transformer.py	683	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2_5_vl/visionmodel.py	224	2	55	35	2	2	2025-03-21	2025-04-10	46404040+lostkevin@users.noreply.github.com	wzuck.wang@gmail.com
megatron_patch/model/qwen2_5_vl/transformer_block.py	434	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_5_vl/transformer_config.py	55	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2_5_vl/model.py	191	1	55	55	1	1	2025-03-21	2025-03-21	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/mixtral/layer_specs.py	129	4	473	148	4	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/__init__.py	1	2	505	473	2	1	2023-12-27	2024-01-28	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/transformer/attention.py	517	3	468	148	3	1	2024-02-02	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/transformer/mlp.py	193	3	468	148	3	1	2024-02-02	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/transformer_config.py	285	4	473	148	4	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/moe/__init__.py	1	1	473	473	1	1	2024-01-28	2024-01-28	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/moe/token_dispatcher.py	303	3	473	148	3	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/moe/moe_layer.py	113	4	473	148	4	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/moe/experts.py	676	4	473	148	4	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/moe/router.py	171	3	473	148	3	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral/model.py	177	3	473	148	3	1	2024-01-28	2024-12-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/glm130b/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/glm130b/gpt_model.py	80	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/glm130b/language_model.py	434	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/glm130b/transformer.py	875	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/chatglm/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/chatglm/gpt_model.py	82	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/chatglm/language_model.py	473	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/chatglm/transformer.py	604	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/chatglm/positional_embeddings.py	60	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/layer_specs.py	120	3	353	119	3	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/__init__.py	1	2	353	119	2	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/multi_latent_attention.py	276	2	119	17	2	2	2025-01-16	2025-04-28	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/deepseek_v2/transformer_layer.py	226	4	353	119	4	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/mlp.py	196	1	119	119	1	1	2025-01-16	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/transformer_block.py	377	4	353	119	4	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/transformer_config.py	42	5	353	17	5	3	2024-05-27	2025-04-28	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/deepseek_v2/moe/shared_experts.py	180	1	119	119	1	1	2025-01-16	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/moe/moe_layer.py	118	2	353	119	2	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/moe/experts.py	676	2	353	119	2	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/deepseek_v2/model.py	181	2	353	119	2	1	2024-05-27	2025-01-16	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/layer_specs.py	86	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/__init__.py	1	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/transformer/attention.py	322	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/transformer/mlp.py	131	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/transformer_config.py	142	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/grouped_gemm_util.py	12	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/__init__.py	1	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/token_dispatcher.py	172	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/moe_layer.py	57	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/moe_utils.py	39	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/experts.py	136	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/moe/router.py	113	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mixtral_bak/model.py	162	1	142	142	1	1	2024-12-24	2024-12-24	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava/__init__.py	1	2	560	555	2	2	2023-11-02	2023-11-07	jerry.lp@alibaba-inc.com	38210876+lwmlyy@users.noreply.github.com
megatron_patch/model/llava/gpt_model.py	89	2	560	555	2	2	2023-11-02	2023-11-07	jerry.lp@alibaba-inc.com	38210876+lwmlyy@users.noreply.github.com
megatron_patch/model/llava/language_model.py	507	7	560	505	7	4	2023-11-02	2023-12-27	jerry.lp@alibaba-inc.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava/transformer.py	1292	3	560	534	3	3	2023-11-02	2023-11-28	jerry.lp@alibaba-inc.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava/clip_encoder.py	75	5	560	503	5	3	2023-11-02	2023-12-29	jerry.lp@alibaba-inc.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava/rotary_pos_embedding.py	54	2	560	555	2	2	2023-11-02	2023-11-07	jerry.lp@alibaba-inc.com	38210876+lwmlyy@users.noreply.github.com
megatron_patch/model/llava/mm_projector_builder.py	37	3	560	503	3	3	2023-11-02	2023-12-29	jerry.lp@alibaba-inc.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3_1/layer_specs.py	85	1	265	265	1	1	2024-08-23	2024-08-23	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/llama3_1/__init__.py	1	1	265	265	1	1	2024-08-23	2024-08-23	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/llama3_1/rms_norm.py	13	1	265	265	1	1	2024-08-23	2024-08-23	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/llama3_1/transformer_config.py	9	1	265	265	1	1	2024-08-23	2024-08-23	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/llama3_1/model.py	201	1	265	265	1	1	2024-08-23	2024-08-23	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5_megablocks/__init__.py	1	1	395	395	1	1	2024-04-15	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5_megablocks/gpt_model.py	88	1	395	395	1	1	2024-04-15	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5_megablocks/language_model.py	453	1	395	395	1	1	2024-04-15	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5_megablocks/transformer.py	1184	2	395	392	2	1	2024-04-15	2024-04-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5_megablocks/rotary_pos_embedding.py	56	1	395	395	1	1	2024-04-15	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/layer_specs.py	92	2	420	395	2	1	2024-03-21	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/__init__.py	1	1	420	420	1	1	2024-03-21	2024-03-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/transformer/attention.py	402	3	420	351	3	1	2024-03-21	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/transformer/mlp.py	164	4	420	351	4	1	2024-03-21	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/transformer_config.py	7	2	420	367	2	1	2024-03-21	2024-05-13	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/moe/__init__.py	1	1	420	420	1	1	2024-03-21	2024-03-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/moe/token_dispatcher.py	282	3	420	351	3	1	2024-03-21	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/moe/moe_layer.py	78	4	420	326	4	1	2024-03-21	2024-06-23	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/moe/experts.py	188	2	420	395	2	1	2024-03-21	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/moe/router.py	139	4	420	349	4	1	2024-03-21	2024-05-31	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen1_5/model.py	144	3	420	351	3	1	2024-03-21	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mistral/__init__.py	1	1	555	555	2	2	2023-11-07	2023-11-07	38210876+lwmlyy@users.noreply.github.com	jerry.lp@alibaba-inc.com
megatron_patch/model/mistral/gpt_model.py	88	1	555	555	2	2	2023-11-07	2023-11-07	38210876+lwmlyy@users.noreply.github.com	jerry.lp@alibaba-inc.com
megatron_patch/model/mistral/language_model.py	466	3	555	393	4	3	2023-11-07	2024-04-17	38210876+lwmlyy@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mistral/transformer.py	1292	2	555	552	3	3	2023-11-07	2023-11-10	38210876+lwmlyy@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mistral/rotary_pos_embedding.py	36	2	555	552	3	3	2023-11-07	2023-11-10	38210876+lwmlyy@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/mistral/modeling_attn_mask_utils.py	121	1	552	552	1	1	2023-11-10	2023-11-10	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/layer_specs.py	108	2	337	170	2	2	2024-06-12	2024-11-26	jerryli1981@users.noreply.github.com	676857171@qq.com
megatron_patch/model/qwen2/transformer_layer.py	147	1	337	337	1	1	2024-06-12	2024-06-12	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/rms_norm.py	13	1	337	337	1	1	2024-06-12	2024-06-12	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/transformer_block.py	323	2	337	328	2	1	2024-06-12	2024-06-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/transformer/attention.py	407	1	337	337	1	1	2024-06-12	2024-06-12	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/transformer/mlp.py	258	3	337	170	3	2	2024-06-12	2024-11-26	jerryli1981@users.noreply.github.com	676857171@qq.com
megatron_patch/model/qwen2/transformer_config.py	14	3	337	328	3	1	2024-06-12	2024-06-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/moe/__init__.py	1	1	337	337	1	1	2024-06-12	2024-06-12	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/moe/token_dispatcher.py	327	2	337	330	2	1	2024-06-12	2024-06-19	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/moe/moe_layer.py	114	7	337	96	8	4	2024-06-12	2025-02-08	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen2/moe/experts.py	316	3	337	170	3	2	2024-06-12	2024-11-26	jerryli1981@users.noreply.github.com	676857171@qq.com
megatron_patch/model/qwen2/moe/router.py	206	3	337	326	3	1	2024-06-12	2024-06-23	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2/model.py	146	2	337	262	2	1	2024-06-12	2024-08-26	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan/gpt_model.py	106	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan/language_model.py	515	2	619	581	2	1	2023-09-04	2023-10-12	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan/transformer.py	1179	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/bloom/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/bloom/gpt_model.py	81	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/bloom/language_model.py	411	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/bloom/transformer.py	811	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/bloom/positional_embeddings.py	122	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/bloom/layers.py	87	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/galactica/__init__.py	1	2	619	616	2	2	2023-09-04	2023-09-07	jerryli1981@users.noreply.github.com	bdshichen@sina.cn
megatron_patch/model/galactica/gpt_model.py	94	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/galactica/language_model.py	501	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/galactica/transformer.py	570	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama/gpt_model.py	92	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama/language_model.py	501	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama/transformer.py	715	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama/positional_embeddings.py	54	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/layer_specs.py	99	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/__init__.py	1	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/llava_model.py	424	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/llava_spec.py	75	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/transformer_config.py	133	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/vision/vit_layer_specs.py	79	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/vision/__init__.py	1	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/vision/clip_vit_model.py	130	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llava_mcore/vision/multimodal_projector.py	41	1	175	175	1	1	2024-11-21	2024-11-21	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan2/gpt_model.py	97	2	604	552	5	2	2023-09-19	2023-11-10	38210876+lwmlyy@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan2/language_model.py	450	4	604	581	6	3	2023-09-19	2023-10-12	jerryli1981@users.noreply.github.com	38210876+lwmlyy@users.noreply.github.com
megatron_patch/model/baichuan2/transformer.py	1292	5	604	574	6	3	2023-09-19	2023-10-19	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/baichuan2/layers.py	134	1	603	603	1	1	2023-09-20	2023-09-20	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen_vl/__init__.py	1	1	505	505	1	1	2023-12-27	2023-12-27	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen_vl/gpt_model.py	89	1	505	505	1	1	2023-12-27	2023-12-27	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen_vl/language_model.py	481	1	505	505	1	1	2023-12-27	2023-12-27	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen_vl/visual.py	296	2	505	503	2	1	2023-12-27	2023-12-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen_vl/transformer.py	1292	1	505	505	1	1	2023-12-27	2023-12-27	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen3_moe/gpt_layer_specs.py	347	1	16	16	1	1	2025-04-29	2025-04-29	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen3_moe/moe_module_specs.py	61	1	16	16	1	1	2025-04-29	2025-04-29	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen3_moe/moe/moe_layer.py	70	1	16	16	1	1	2025-04-29	2025-04-29	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen3_moe/moe/moe_utils.py	79	1	16	16	1	1	2025-04-29	2025-04-29	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/qwen3_moe/moe/router.py	111	1	16	16	1	1	2025-04-29	2025-04-29	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/model/falcon/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/falcon/gpt_model.py	94	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/falcon/language_model.py	491	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/falcon/transformer.py	845	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama2/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama2/gpt_model.py	88	2	619	583	3	3	2023-09-04	2023-10-10	jerryli1981@users.noreply.github.com	jerry.lp@alibaba-inc.com
megatron_patch/model/llama2/language_model.py	454	8	619	436	11	3	2023-09-04	2024-03-05	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama2/transformer.py	1296	13	619	442	17	4	2023-09-04	2024-02-28	jerryli1981@users.noreply.github.com	38210876+lwmlyy@users.noreply.github.com
megatron_patch/model/llama2/rotary_pos_embedding.py	56	4	582	535	5	3	2023-10-11	2023-11-27	jerry.lp@alibaba-inc.com	lwmlyy@163.com
megatron_patch/model/llama3/layer_specs.py	85	2	357	308	2	1	2024-05-23	2024-07-11	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/__init__.py	1	1	357	357	1	1	2024-05-23	2024-05-23	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/gpt_model.py	88	2	389	351	2	1	2024-04-21	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/language_model.py	438	3	389	351	3	1	2024-04-21	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/rms_norm.py	13	1	308	308	1	1	2024-07-11	2024-07-11	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/transformer/attention.py	402	2	357	351	2	1	2024-05-23	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/transformer/mlp.py	150	2	357	351	2	1	2024-05-23	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/transformer_config.py	8	1	308	308	1	1	2024-07-11	2024-07-11	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/transformer_legacy.py	1252	2	357	351	2	1	2024-05-23	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/llama3/model.py	144	2	357	351	2	1	2024-05-23	2024-05-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen2_moe/layer_specs.py	281	1	64	64	1	1	2025-03-12	2025-03-12	qianwan@ymail.com	qianwan@ymail.com
megatron_patch/model/qwen2_moe/__init__.py	1	1	64	64	1	1	2025-03-12	2025-03-12	qianwan@ymail.com	qianwan@ymail.com
megatron_patch/model/qwen2_moe/transformer_config.py	55	1	64	64	1	1	2025-03-12	2025-03-12	qianwan@ymail.com	qianwan@ymail.com
megatron_patch/model/qwen/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen/gpt_model.py	88	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen/language_model.py	440	2	619	581	2	1	2023-09-04	2023-10-12	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/qwen/transformer.py	1243	5	619	468	5	1	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/starcoder/__init__.py	1	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/starcoder/gpt_model.py	83	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/starcoder/language_model.py	387	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/starcoder/glu_activations.py	32	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/starcoder/transformer.py	848	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/model/starcoder/enums.py	19	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/__init__.py	1	2	619	616	2	2	2023-09-04	2023-09-07	jerryli1981@users.noreply.github.com	bdshichen@sina.cn
megatron_patch/finetune_utils.py	202	6	619	336	8	4	2023-09-04	2024-06-13	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/training.py	612	8	619	468	9	3	2023-09-04	2024-02-02	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/arguments.py	449	35	619	17	37	5	2023-09-04	2025-04-28	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/template/helper.py	115	6	83	6	6	2	2025-02-21	2025-05-09	jerryli1981@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/lm_evaluate.py	139	3	468	395	3	2	2024-02-02	2024-04-15	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/tokenizer/tokenization_baichuan.py	139	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/tokenizer/tokenization_qwen_vl.py	441	2	505	503	2	1	2023-12-27	2023-12-29	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/tokenizer/tokenization_yi.py	166	1	544	544	1	1	2023-11-18	2023-11-18	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/tokenizer/jiebabpe_tokenizer.py	53	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/tokenizer/icetk_glm130b_tokenizer.py	273	1	619	619	1	1	2023-09-04	2023-09-04	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com
megatron_patch/tensor_parallel.py	66	1	139	139	1	1	2024-12-27	2024-12-27	46404040+lostkevin@users.noreply.github.com	46404040+lostkevin@users.noreply.github.com
megatron_patch/initialize.py	91	2	505	473	2	1	2023-12-27	2024-01-28	jerryli1981@users.noreply.github.com	jerryli1981@users.noreply.github.com