Zzong's Notes

❯

machine_learning

❯

❯

LLM

38개의 글

inference
Alpaca
AWQ
- quantization
channel(LLM)
Decoupled Clip and Dynamic sAmpling Policy Optimization
deepspeed
- deep_learning
- LLM
DistributedDataParallel
- deep_learning
- LLM
DPO
- LLM
Exaone 3.0
- LG
FP8 Quantization
Fully Sharded Data Parallel
- huggingface
- accelerate
Generalized Knowledge Distillation
- LLM
- distillation
GPT
- NLP
- LLM
GPT-2
- LLM
Group Relative Policy Optimization
- reinforcement_learning
- LLM
Group Sequence Policy Optimization
Large Language Model
- NLP
- LLM
Llama
- LLM
llm_as_classifier
- LLM
LoRA
- LLM
LVLM 를 따라하는 정보 넣기
- LLM
- LVLM
MoE
On-Policy Distillation
Open challenges in LLM research
- LLM
- research
Parallelism
Prompt Engineering
- LLM
- NLP
Proximal Policy Optimization
- reinforcement_learning
- LLM
Quantization
- deep_learning
- quantization
reward model
RLHF
- LLM
- reinforcement_learning
SimLM
- embedding
supervised fine-tuning
T5
- summarization
- LLM
Train Large Model
- LLM
- deepspeed
Trainer(huggingface)
- huggingface
- LLM
TrainerCallback
vicuna
- LLM
자연스러운 한국어를 위한 LLM Post-Training