JaheimLee's picture

JaheimLee

JaheimLee

·

JaheimLee

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

RedHatAI/Qwen3-32B-FP8-dynamic

new activity 9 days ago

Qwen/Qwen3-30B-A3B:Minor changes, big gains -- Huggingface MoE modeling enhancement

liked a model 19 days ago

Skywork/SkyReels-V2-I2V-14B-540P

View all activity

Organizations

JaheimLee's activity

New activity in Qwen/Qwen3-30B-A3B 9 days ago

Minor changes, big gains -- Huggingface MoE modeling enhancement

#13 opened 10 days ago by

New activity in neavo/modern_bert_multilingual 3 months ago

NER任务

#1 opened 3 months ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-32B 4 months ago

Tokenizer config is wrong

#10 opened 4 months ago by

New activity in mattshumer/Reflection-Llama-3.1-70B 8 months ago

4bit model

#13 opened 8 months ago by

New activity in OpenBuddy/openbuddy-mixtral-8x7b-v16.1-32k over 1 year ago

更小尺寸的MOE

#2 opened over 1 year ago by

New activity in OpenBuddy/openbuddy-mixtral-8x7b-v15.3 over 1 year ago

你好作者，15.3比起15.1和15.2的区别在哪呀？

#1 opened over 1 year ago by

New activity in baichuan-inc/Baichuan2-13B-Chat over 1 year ago

由用户自定义是否使用xformers

#1 opened over 1 year ago by

Update config.json

#3 opened over 1 year ago by

New activity in baichuan-inc/Baichuan2-7B-Chat over 1 year ago

NormHead 中的分支判断

#3 opened over 1 year ago by

New activity in Qwen/Qwen-7B-Chat over 1 year ago

fix deepspeed trainning issue

#24 opened almost 2 years ago by

New activity in Qwen/Qwen-7B-Chat almost 2 years ago

tokenizer无法在文本中切分special token

#1 opened almost 2 years ago by

New activity in fb700/chatglm-fitness-RLHF almost 2 years ago

chatglm2-6b-32k

#7 opened almost 2 years ago by

New activity in Linly-AI/Chinese-LLaMA-2-7B-hf almost 2 years ago

tokenizer config好像有些问题

#2 opened almost 2 years ago by

New activity in fireballoon/baichuan-vicuna-7b almost 2 years ago

fast tokenizer问题

#3 opened almost 2 years ago by

New activity in qhduan/aquilachat-7b almost 2 years ago

The usage

#1 opened almost 2 years ago by

The usage

#1 opened almost 2 years ago by