yi_lu/pretrain_kaiyuan2b
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: update README and model inference testing scripts

Browse Source
This commit is contained in:
路易
2026-05-06 18:35:53 +08:00
parent 404f1b85aa
commit 056df3b6ca
3 changed files with 105 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
scripts/kaiyuan2b-training/eval_smoke_gpt2.sh
View File

@@ -24,27 +24,6 @@ export CUDA_DEVICE_MAX_CONNECTIONS=1
# pip install flask-restful
# torchrun $DISTRIBUTED_ARGS $MEGATRON_PATH/tools/run_text_generation_server.py \
# --tensor-model-parallel-size 1 \
# --pipeline-model-parallel-size 1 \
# --num-layers 12 \
# --hidden-size 3072 \
# --load ${CHECKPOINT} \
# --num-attention-heads 8 \
# --num-query-groups 4 \
# --max-position-embeddings 4096 \
# --fp16 \
# --micro-batch-size 1 \
# --seq-length 1024 \
# --temperature 1.0 \
# --top_p 0.9 \
# --seed 42 \
# --tokenizer-type GPT2BPETokenizer
# --vocab-file $VOCAB_FILE \
# --merge-file $MERGE_FILE \
torchrun $DISTRIBUTED_ARGS $MEGATRON_PATH/tools/run_text_generation_server.py \
--load $CHECKPOINT \
--tensor-model-parallel-size 1 \